diff options
author | Len Brown <len.brown@intel.com> | 2009-01-09 03:39:43 -0500 |
---|---|---|
committer | Len Brown <len.brown@intel.com> | 2009-01-09 03:39:43 -0500 |
commit | b2576e1d4408e134e2188c967b1f28af39cd79d4 (patch) | |
tree | 004f3c82faab760f304ce031d6d2f572e7746a50 /kernel | |
parent | 3cc8a5f4ba91f67bbdb81a43a99281a26aab8d77 (diff) | |
parent | 2150edc6c5cf00f7adb54538b9ea2a3e9cedca3f (diff) | |
download | kernel_samsung_smdk4412-b2576e1d4408e134e2188c967b1f28af39cd79d4.zip kernel_samsung_smdk4412-b2576e1d4408e134e2188c967b1f28af39cd79d4.tar.gz kernel_samsung_smdk4412-b2576e1d4408e134e2188c967b1f28af39cd79d4.tar.bz2 |
Merge branch 'linus' into release
Diffstat (limited to 'kernel')
120 files changed, 12357 insertions, 4747 deletions
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 9fdba03..bf987b9 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -52,28 +52,3 @@ config PREEMPT endchoice -config PREEMPT_RCU - bool "Preemptible RCU" - depends on PREEMPT - default n - help - This option reduces the latency of the kernel by making certain - RCU sections preemptible. Normally RCU code is non-preemptible, if - this option is selected then read-only RCU sections become - preemptible. This helps latency, but may expose bugs due to - now-naive assumptions about each RCU read-side critical section - remaining on a given CPU through its execution. - - Say N if you are unsure. - -config RCU_TRACE - bool "Enable tracing for RCU - currently stats in debugfs" - depends on PREEMPT_RCU - select DEBUG_FS - default y - help - This option provides tracing in RCU which presents stats - in debugfs for debugging RCU implementation. - - Say Y here if you want to enable RCU tracing - Say N if you are unsure. diff --git a/kernel/Makefile b/kernel/Makefile index 19fad00..2921d90 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -9,7 +9,8 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ - notifier.o ksysfs.o pm_qos_params.o sched_clock.o + notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ + async.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files @@ -19,7 +20,6 @@ CFLAGS_REMOVE_mutex-debug.o = -pg CFLAGS_REMOVE_rtmutex-debug.o = -pg CFLAGS_REMOVE_cgroup-debug.o = -pg CFLAGS_REMOVE_sched_clock.o = -pg -CFLAGS_REMOVE_sched.o = -pg endif obj-$(CONFIG_FREEZER) += freezer.o @@ -74,10 +74,10 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_CLASSIC_RCU) += rcuclassic.o +obj-$(CONFIG_TREE_RCU) += rcutree.o obj-$(CONFIG_PREEMPT_RCU) += rcupreempt.o -ifeq ($(CONFIG_PREEMPT_RCU),y) -obj-$(CONFIG_RCU_TRACE) += rcupreempt_trace.o -endif +obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o +obj-$(CONFIG_PREEMPT_RCU_TRACE) += rcupreempt_trace.o obj-$(CONFIG_RELAY) += relay.o obj-$(CONFIG_SYSCTL) += utsname_sysctl.o obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o @@ -90,7 +90,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o -ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y) +ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is # needed for x86 only. Why this used to be enabled for all architectures is beyond # me. I suspect most platforms don't need this, but until we know that for sure diff --git a/kernel/acct.c b/kernel/acct.c index f6006a6..d57b7cb 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -530,15 +530,14 @@ static void do_acct_process(struct bsd_acct_struct *acct, do_div(elapsed, AHZ); ac.ac_btime = get_seconds() - elapsed; /* we really need to bite the bullet and change layout */ - ac.ac_uid = current->uid; - ac.ac_gid = current->gid; + current_uid_gid(&ac.ac_uid, &ac.ac_gid); #if ACCT_VERSION==2 ac.ac_ahz = AHZ; #endif #if ACCT_VERSION==1 || ACCT_VERSION==2 /* backward-compatible 16 bit fields */ - ac.ac_uid16 = current->uid; - ac.ac_gid16 = current->gid; + ac.ac_uid16 = ac.ac_uid; + ac.ac_gid16 = ac.ac_gid; #endif #if ACCT_VERSION==3 ac.ac_pid = task_tgid_nr_ns(current, ns); diff --git a/kernel/async.c b/kernel/async.c new file mode 100644 index 0000000..64cc916 --- /dev/null +++ b/kernel/async.c @@ -0,0 +1,323 @@ +/* + * async.c: Asynchronous function calls for boot performance + * + * (C) Copyright 2009 Intel Corporation + * Author: Arjan van de Ven <arjan@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + + +/* + +Goals and Theory of Operation + +The primary goal of this feature is to reduce the kernel boot time, +by doing various independent hardware delays and discovery operations +decoupled and not strictly serialized. + +More specifically, the asynchronous function call concept allows +certain operations (primarily during system boot) to happen +asynchronously, out of order, while these operations still +have their externally visible parts happen sequentially and in-order. +(not unlike how out-of-order CPUs retire their instructions in order) + +Key to the asynchronous function call implementation is the concept of +a "sequence cookie" (which, although it has an abstracted type, can be +thought of as a monotonically incrementing number). + +The async core will assign each scheduled event such a sequence cookie and +pass this to the called functions. + +The asynchronously called function should before doing a globally visible +operation, such as registering device numbers, call the +async_synchronize_cookie() function and pass in its own cookie. The +async_synchronize_cookie() function will make sure that all asynchronous +operations that were scheduled prior to the operation corresponding with the +cookie have completed. + +Subsystem/driver initialization code that scheduled asynchronous probe +functions, but which shares global resources with other drivers/subsystems +that do not use the asynchronous call feature, need to do a full +synchronization with the async_synchronize_full() function, before returning +from their init function. This is to maintain strict ordering between the +asynchronous and synchronous parts of the kernel. + +*/ + +#include <linux/async.h> +#include <linux/module.h> +#include <linux/wait.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/kthread.h> +#include <asm/atomic.h> + +static async_cookie_t next_cookie = 1; + +#define MAX_THREADS 256 +#define MAX_WORK 32768 + +static LIST_HEAD(async_pending); +static LIST_HEAD(async_running); +static DEFINE_SPINLOCK(async_lock); + +struct async_entry { + struct list_head list; + async_cookie_t cookie; + async_func_ptr *func; + void *data; + struct list_head *running; +}; + +static DECLARE_WAIT_QUEUE_HEAD(async_done); +static DECLARE_WAIT_QUEUE_HEAD(async_new); + +static atomic_t entry_count; +static atomic_t thread_count; + +extern int initcall_debug; + + +/* + * MUST be called with the lock held! + */ +static async_cookie_t __lowest_in_progress(struct list_head *running) +{ + struct async_entry *entry; + if (!list_empty(&async_pending)) { + entry = list_first_entry(&async_pending, + struct async_entry, list); + return entry->cookie; + } else if (!list_empty(running)) { + entry = list_first_entry(running, + struct async_entry, list); + return entry->cookie; + } else { + /* nothing in progress... next_cookie is "infinity" */ + return next_cookie; + } + +} +/* + * pick the first pending entry and run it + */ +static void run_one_entry(void) +{ + unsigned long flags; + struct async_entry *entry; + ktime_t calltime, delta, rettime; + + /* 1) pick one task from the pending queue */ + + spin_lock_irqsave(&async_lock, flags); + if (list_empty(&async_pending)) + goto out; + entry = list_first_entry(&async_pending, struct async_entry, list); + + /* 2) move it to the running queue */ + list_del(&entry->list); + list_add_tail(&entry->list, &async_running); + spin_unlock_irqrestore(&async_lock, flags); + + /* 3) run it (and print duration)*/ + if (initcall_debug && system_state == SYSTEM_BOOTING) { + printk("calling %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current)); + calltime = ktime_get(); + } + entry->func(entry->data, entry->cookie); + if (initcall_debug && system_state == SYSTEM_BOOTING) { + rettime = ktime_get(); + delta = ktime_sub(rettime, calltime); + printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie, + entry->func, ktime_to_ns(delta) >> 10); + } + + /* 4) remove it from the running queue */ + spin_lock_irqsave(&async_lock, flags); + list_del(&entry->list); + + /* 5) free the entry */ + kfree(entry); + atomic_dec(&entry_count); + + spin_unlock_irqrestore(&async_lock, flags); + + /* 6) wake up any waiters. */ + wake_up(&async_done); + return; + +out: + spin_unlock_irqrestore(&async_lock, flags); +} + + +static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct list_head *running) +{ + struct async_entry *entry; + unsigned long flags; + async_cookie_t newcookie; + + + /* allow irq-off callers */ + entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC); + + /* + * If we're out of memory or if there's too much work + * pending already, we execute synchronously. + */ + if (!entry || atomic_read(&entry_count) > MAX_WORK) { + kfree(entry); + spin_lock_irqsave(&async_lock, flags); + newcookie = next_cookie++; + spin_unlock_irqrestore(&async_lock, flags); + + /* low on memory.. run synchronously */ + ptr(data, newcookie); + return newcookie; + } + entry->func = ptr; + entry->data = data; + entry->running = running; + + spin_lock_irqsave(&async_lock, flags); + newcookie = entry->cookie = next_cookie++; + list_add_tail(&entry->list, &async_pending); + atomic_inc(&entry_count); + spin_unlock_irqrestore(&async_lock, flags); + wake_up(&async_new); + return newcookie; +} + +async_cookie_t async_schedule(async_func_ptr *ptr, void *data) +{ + return __async_schedule(ptr, data, &async_pending); +} +EXPORT_SYMBOL_GPL(async_schedule); + +async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running) +{ + return __async_schedule(ptr, data, running); +} +EXPORT_SYMBOL_GPL(async_schedule_special); + +void async_synchronize_full(void) +{ + do { + async_synchronize_cookie(next_cookie); + } while (!list_empty(&async_running) || !list_empty(&async_pending)); +} +EXPORT_SYMBOL_GPL(async_synchronize_full); + +void async_synchronize_full_special(struct list_head *list) +{ + async_synchronize_cookie_special(next_cookie, list); +} +EXPORT_SYMBOL_GPL(async_synchronize_full_special); + +void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running) +{ + ktime_t starttime, delta, endtime; + + if (initcall_debug && system_state == SYSTEM_BOOTING) { + printk("async_waiting @ %i\n", task_pid_nr(current)); + starttime = ktime_get(); + } + + wait_event(async_done, __lowest_in_progress(running) >= cookie); + + if (initcall_debug && system_state == SYSTEM_BOOTING) { + endtime = ktime_get(); + delta = ktime_sub(endtime, starttime); + + printk("async_continuing @ %i after %lli usec\n", + task_pid_nr(current), ktime_to_ns(delta) >> 10); + } +} +EXPORT_SYMBOL_GPL(async_synchronize_cookie_special); + +void async_synchronize_cookie(async_cookie_t cookie) +{ + async_synchronize_cookie_special(cookie, &async_running); +} +EXPORT_SYMBOL_GPL(async_synchronize_cookie); + + +static int async_thread(void *unused) +{ + DECLARE_WAITQUEUE(wq, current); + add_wait_queue(&async_new, &wq); + + while (!kthread_should_stop()) { + int ret = HZ; + set_current_state(TASK_INTERRUPTIBLE); + /* + * check the list head without lock.. false positives + * are dealt with inside run_one_entry() while holding + * the lock. + */ + rmb(); + if (!list_empty(&async_pending)) + run_one_entry(); + else + ret = schedule_timeout(HZ); + + if (ret == 0) { + /* + * we timed out, this means we as thread are redundant. + * we sign off and die, but we to avoid any races there + * is a last-straw check to see if work snuck in. + */ + atomic_dec(&thread_count); + wmb(); /* manager must see our departure first */ + if (list_empty(&async_pending)) + break; + /* + * woops work came in between us timing out and us + * signing off; we need to stay alive and keep working. + */ + atomic_inc(&thread_count); + } + } + remove_wait_queue(&async_new, &wq); + + return 0; +} + +static int async_manager_thread(void *unused) +{ + DECLARE_WAITQUEUE(wq, current); + add_wait_queue(&async_new, &wq); + + while (!kthread_should_stop()) { + int tc, ec; + + set_current_state(TASK_INTERRUPTIBLE); + + tc = atomic_read(&thread_count); + rmb(); + ec = atomic_read(&entry_count); + + while (tc < ec && tc < MAX_THREADS) { + kthread_run(async_thread, NULL, "async/%i", tc); + atomic_inc(&thread_count); + tc++; + } + + schedule(); + } + remove_wait_queue(&async_new, &wq); + + return 0; +} + +static int __init async_init(void) +{ + kthread_run(async_manager_thread, NULL, "async/mgr"); + return 0; +} + +core_initcall(async_init); diff --git a/kernel/audit.h b/kernel/audit.h index 9d67174..16f18ca 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -159,11 +159,8 @@ static inline int audit_signal_info(int sig, struct task_struct *t) return __audit_signal_info(sig, t); return 0; } -extern enum audit_state audit_filter_inodes(struct task_struct *, - struct audit_context *); -extern void audit_set_auditable(struct audit_context *); +extern void audit_filter_inodes(struct task_struct *, struct audit_context *); #else #define audit_signal_info(s,t) AUDIT_DISABLED #define audit_filter_inodes(t,c) AUDIT_DISABLED -#define audit_set_auditable(c) #endif diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 8b50944..8ad9545 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -450,6 +450,7 @@ static void kill_rules(struct audit_tree *tree) audit_log_end(ab); rule->tree = NULL; list_del_rcu(&entry->list); + list_del(&entry->rule.list); call_rcu(&entry->rcu, audit_free_rule_rcu); } } @@ -617,7 +618,7 @@ int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op) if (pathname[0] != '/' || rule->listnr != AUDIT_FILTER_EXIT || - op & ~AUDIT_EQUAL || + op != Audit_equal || rule->inode_f || rule->watch || rule->tree) return -EINVAL; rule->tree = alloc_tree(pathname); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 9fd85a4..fbf24d1 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -86,6 +86,14 @@ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { #error Fix audit_filter_list initialiser #endif }; +static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { + LIST_HEAD_INIT(audit_rules_list[0]), + LIST_HEAD_INIT(audit_rules_list[1]), + LIST_HEAD_INIT(audit_rules_list[2]), + LIST_HEAD_INIT(audit_rules_list[3]), + LIST_HEAD_INIT(audit_rules_list[4]), + LIST_HEAD_INIT(audit_rules_list[5]), +}; DEFINE_MUTEX(audit_filter_mutex); @@ -244,7 +252,8 @@ static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { if (krule->listnr != AUDIT_FILTER_EXIT || - krule->watch || krule->inode_f || krule->tree) + krule->watch || krule->inode_f || krule->tree || + (f->op != Audit_equal && f->op != Audit_not_equal)) return -EINVAL; krule->inode_f = f; @@ -262,7 +271,7 @@ static int audit_to_watch(struct audit_krule *krule, char *path, int len, if (path[0] != '/' || path[len-1] == '/' || krule->listnr != AUDIT_FILTER_EXIT || - op & ~AUDIT_EQUAL || + op != Audit_equal || krule->inode_f || krule->watch || krule->tree) return -EINVAL; @@ -412,12 +421,32 @@ exit_err: return ERR_PTR(err); } +static u32 audit_ops[] = +{ + [Audit_equal] = AUDIT_EQUAL, + [Audit_not_equal] = AUDIT_NOT_EQUAL, + [Audit_bitmask] = AUDIT_BIT_MASK, + [Audit_bittest] = AUDIT_BIT_TEST, + [Audit_lt] = AUDIT_LESS_THAN, + [Audit_gt] = AUDIT_GREATER_THAN, + [Audit_le] = AUDIT_LESS_THAN_OR_EQUAL, + [Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL, +}; + +static u32 audit_to_op(u32 op) +{ + u32 n; + for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++) + ; + return n; +} + + /* Translate struct audit_rule to kernel's rule respresentation. * Exists for backward compatibility with userspace. */ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule) { struct audit_entry *entry; - struct audit_field *ino_f; int err = 0; int i; @@ -427,12 +456,28 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule) for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; + u32 n; + + n = rule->fields[i] & (AUDIT_NEGATE|AUDIT_OPERATORS); + + /* Support for legacy operators where + * AUDIT_NEGATE bit signifies != and otherwise assumes == */ + if (n & AUDIT_NEGATE) + f->op = Audit_not_equal; + else if (!n) + f->op = Audit_equal; + else + f->op = audit_to_op(n); + + entry->rule.vers_ops = (n & AUDIT_OPERATORS) ? 2 : 1; - f->op = rule->fields[i] & (AUDIT_NEGATE|AUDIT_OPERATORS); f->type = rule->fields[i] & ~(AUDIT_NEGATE|AUDIT_OPERATORS); f->val = rule->values[i]; err = -EINVAL; + if (f->op == Audit_bad) + goto exit_free; + switch(f->type) { default: goto exit_free; @@ -454,11 +499,8 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule) case AUDIT_EXIT: case AUDIT_SUCCESS: /* bit ops are only useful on syscall args */ - if (f->op == AUDIT_BIT_MASK || - f->op == AUDIT_BIT_TEST) { - err = -EINVAL; + if (f->op == Audit_bitmask || f->op == Audit_bittest) goto exit_free; - } break; case AUDIT_ARG0: case AUDIT_ARG1: @@ -467,11 +509,8 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule) break; /* arch is only allowed to be = or != */ case AUDIT_ARCH: - if ((f->op != AUDIT_NOT_EQUAL) && (f->op != AUDIT_EQUAL) - && (f->op != AUDIT_NEGATE) && (f->op)) { - err = -EINVAL; + if (f->op != Audit_not_equal && f->op != Audit_equal) goto exit_free; - } entry->rule.arch_f = f; break; case AUDIT_PERM: @@ -488,33 +527,10 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule) goto exit_free; break; } - - entry->rule.vers_ops = (f->op & AUDIT_OPERATORS) ? 2 : 1; - - /* Support for legacy operators where - * AUDIT_NEGATE bit signifies != and otherwise assumes == */ - if (f->op & AUDIT_NEGATE) - f->op = AUDIT_NOT_EQUAL; - else if (!f->op) - f->op = AUDIT_EQUAL; - else if (f->op == AUDIT_OPERATORS) { - err = -EINVAL; - goto exit_free; - } } - ino_f = entry->rule.inode_f; - if (ino_f) { - switch(ino_f->op) { - case AUDIT_NOT_EQUAL: - entry->rule.inode_f = NULL; - case AUDIT_EQUAL: - break; - default: - err = -EINVAL; - goto exit_free; - } - } + if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal) + entry->rule.inode_f = NULL; exit_nofree: return entry; @@ -530,7 +546,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, { int err = 0; struct audit_entry *entry; - struct audit_field *ino_f; void *bufp; size_t remain = datasz - sizeof(struct audit_rule_data); int i; @@ -546,11 +561,11 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, struct audit_field *f = &entry->rule.fields[i]; err = -EINVAL; - if (!(data->fieldflags[i] & AUDIT_OPERATORS) || - data->fieldflags[i] & ~AUDIT_OPERATORS) + + f->op = audit_to_op(data->fieldflags[i]); + if (f->op == Audit_bad) goto exit_free; - f->op = data->fieldflags[i] & AUDIT_OPERATORS; f->type = data->fields[i]; f->val = data->values[i]; f->lsm_str = NULL; @@ -662,18 +677,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, } } - ino_f = entry->rule.inode_f; - if (ino_f) { - switch(ino_f->op) { - case AUDIT_NOT_EQUAL: - entry->rule.inode_f = NULL; - case AUDIT_EQUAL: - break; - default: - err = -EINVAL; - goto exit_free; - } - } + if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal) + entry->rule.inode_f = NULL; exit_nofree: return entry; @@ -713,10 +718,10 @@ static struct audit_rule *audit_krule_to_rule(struct audit_krule *krule) rule->fields[i] = krule->fields[i].type; if (krule->vers_ops == 1) { - if (krule->fields[i].op & AUDIT_NOT_EQUAL) + if (krule->fields[i].op == Audit_not_equal) rule->fields[i] |= AUDIT_NEGATE; } else { - rule->fields[i] |= krule->fields[i].op; + rule->fields[i] |= audit_ops[krule->fields[i].op]; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) rule->mask[i] = krule->mask[i]; @@ -744,7 +749,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) struct audit_field *f = &krule->fields[i]; data->fields[i] = f->type; - data->fieldflags[i] = f->op; + data->fieldflags[i] = audit_ops[f->op]; switch(f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: @@ -919,6 +924,7 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old, new->action = old->action; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) new->mask[i] = old->mask[i]; + new->prio = old->prio; new->buflen = old->buflen; new->inode_f = old->inode_f; new->watch = NULL; @@ -987,9 +993,8 @@ static void audit_update_watch(struct audit_parent *parent, /* If the update involves invalidating rules, do the inode-based * filtering now, so we don't omit records. */ - if (invalidating && current->audit_context && - audit_filter_inodes(current, current->audit_context) == AUDIT_RECORD_CONTEXT) - audit_set_auditable(current->audit_context); + if (invalidating && current->audit_context) + audit_filter_inodes(current, current->audit_context); nwatch = audit_dupe_watch(owatch); if (IS_ERR(nwatch)) { @@ -1007,12 +1012,15 @@ static void audit_update_watch(struct audit_parent *parent, list_del_rcu(&oentry->list); nentry = audit_dupe_rule(&oentry->rule, nwatch); - if (IS_ERR(nentry)) + if (IS_ERR(nentry)) { + list_del(&oentry->rule.list); audit_panic("error updating watch, removing"); - else { + } else { int h = audit_hash_ino((u32)ino); list_add(&nentry->rule.rlist, &nwatch->rules); list_add_rcu(&nentry->list, &audit_inode_hash[h]); + list_replace(&oentry->rule.list, + &nentry->rule.list); } call_rcu(&oentry->rcu, audit_free_rule_rcu); @@ -1077,6 +1085,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent) audit_log_end(ab); } list_del(&r->rlist); + list_del(&r->list); list_del_rcu(&e->list); call_rcu(&e->rcu, audit_free_rule_rcu); } @@ -1102,12 +1111,16 @@ static void audit_inotify_unregister(struct list_head *in_list) /* Find an existing audit rule. * Caller must hold audit_filter_mutex to prevent stale rule data. */ static struct audit_entry *audit_find_rule(struct audit_entry *entry, - struct list_head *list) + struct list_head **p) { struct audit_entry *e, *found = NULL; + struct list_head *list; int h; - if (entry->rule.watch) { + if (entry->rule.inode_f) { + h = audit_hash_ino(entry->rule.inode_f->val); + *p = list = &audit_inode_hash[h]; + } else if (entry->rule.watch) { /* we don't know the inode number, so must walk entire hash */ for (h = 0; h < AUDIT_INODE_BUCKETS; h++) { list = &audit_inode_hash[h]; @@ -1118,6 +1131,8 @@ static struct audit_entry *audit_find_rule(struct audit_entry *entry, } } goto out; + } else { + *p = list = &audit_filter_list[entry->rule.listnr]; } list_for_each_entry(e, list, list) @@ -1258,15 +1273,17 @@ static int audit_add_watch(struct audit_krule *krule, struct nameidata *ndp, return ret; } +static u64 prio_low = ~0ULL/2; +static u64 prio_high = ~0ULL/2 - 1; + /* Add rule to given filterlist if not a duplicate. */ -static inline int audit_add_rule(struct audit_entry *entry, - struct list_head *list) +static inline int audit_add_rule(struct audit_entry *entry) { struct audit_entry *e; - struct audit_field *inode_f = entry->rule.inode_f; struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; struct nameidata *ndp = NULL, *ndw = NULL; + struct list_head *list; int h, err; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; @@ -1277,13 +1294,8 @@ static inline int audit_add_rule(struct audit_entry *entry, dont_count = 1; #endif - if (inode_f) { - h = audit_hash_ino(inode_f->val); - list = &audit_inode_hash[h]; - } - mutex_lock(&audit_filter_mutex); - e = audit_find_rule(entry, list); + e = audit_find_rule(entry, &list); mutex_unlock(&audit_filter_mutex); if (e) { err = -EEXIST; @@ -1319,10 +1331,22 @@ static inline int audit_add_rule(struct audit_entry *entry, } } + entry->rule.prio = ~0ULL; + if (entry->rule.listnr == AUDIT_FILTER_EXIT) { + if (entry->rule.flags & AUDIT_FILTER_PREPEND) + entry->rule.prio = ++prio_high; + else + entry->rule.prio = --prio_low; + } + if (entry->rule.flags & AUDIT_FILTER_PREPEND) { + list_add(&entry->rule.list, + &audit_rules_list[entry->rule.listnr]); list_add_rcu(&entry->list, list); entry->rule.flags &= ~AUDIT_FILTER_PREPEND; } else { + list_add_tail(&entry->rule.list, + &audit_rules_list[entry->rule.listnr]); list_add_tail_rcu(&entry->list, list); } #ifdef CONFIG_AUDITSYSCALL @@ -1345,15 +1369,14 @@ error: } /* Remove an existing rule from filterlist. */ -static inline int audit_del_rule(struct audit_entry *entry, - struct list_head *list) +static inline int audit_del_rule(struct audit_entry *entry) { struct audit_entry *e; - struct audit_field *inode_f = entry->rule.inode_f; struct audit_watch *watch, *tmp_watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; + struct list_head *list; LIST_HEAD(inotify_list); - int h, ret = 0; + int ret = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; @@ -1363,13 +1386,8 @@ static inline int audit_del_rule(struct audit_entry *entry, dont_count = 1; #endif - if (inode_f) { - h = audit_hash_ino(inode_f->val); - list = &audit_inode_hash[h]; - } - mutex_lock(&audit_filter_mutex); - e = audit_find_rule(entry, list); + e = audit_find_rule(entry, &list); if (!e) { mutex_unlock(&audit_filter_mutex); ret = -ENOENT; @@ -1404,6 +1422,7 @@ static inline int audit_del_rule(struct audit_entry *entry, audit_remove_tree_rule(&e->rule); list_del_rcu(&e->list); + list_del(&e->rule.list); call_rcu(&e->rcu, audit_free_rule_rcu); #ifdef CONFIG_AUDITSYSCALL @@ -1432,30 +1451,16 @@ out: static void audit_list(int pid, int seq, struct sk_buff_head *q) { struct sk_buff *skb; - struct audit_entry *entry; + struct audit_krule *r; int i; /* This is a blocking read, so use audit_filter_mutex instead of rcu * iterator to sync with list writers. */ for (i=0; i<AUDIT_NR_FILTERS; i++) { - list_for_each_entry(entry, &audit_filter_list[i], list) { - struct audit_rule *rule; - - rule = audit_krule_to_rule(&entry->rule); - if (unlikely(!rule)) - break; - skb = audit_make_reply(pid, seq, AUDIT_LIST, 0, 1, - rule, sizeof(*rule)); - if (skb) - skb_queue_tail(q, skb); - kfree(rule); - } - } - for (i = 0; i < AUDIT_INODE_BUCKETS; i++) { - list_for_each_entry(entry, &audit_inode_hash[i], list) { + list_for_each_entry(r, &audit_rules_list[i], list) { struct audit_rule *rule; - rule = audit_krule_to_rule(&entry->rule); + rule = audit_krule_to_rule(r); if (unlikely(!rule)) break; skb = audit_make_reply(pid, seq, AUDIT_LIST, 0, 1, @@ -1474,30 +1479,16 @@ static void audit_list(int pid, int seq, struct sk_buff_head *q) static void audit_list_rules(int pid, int seq, struct sk_buff_head *q) { struct sk_buff *skb; - struct audit_entry *e; + struct audit_krule *r; int i; /* This is a blocking read, so use audit_filter_mutex instead of rcu * iterator to sync with list writers. */ for (i=0; i<AUDIT_NR_FILTERS; i++) { - list_for_each_entry(e, &audit_filter_list[i], list) { - struct audit_rule_data *data; - - data = audit_krule_to_data(&e->rule); - if (unlikely(!data)) - break; - skb = audit_make_reply(pid, seq, AUDIT_LIST_RULES, 0, 1, - data, sizeof(*data) + data->buflen); - if (skb) - skb_queue_tail(q, skb); - kfree(data); - } - } - for (i=0; i< AUDIT_INODE_BUCKETS; i++) { - list_for_each_entry(e, &audit_inode_hash[i], list) { + list_for_each_entry(r, &audit_rules_list[i], list) { struct audit_rule_data *data; - data = audit_krule_to_data(&e->rule); + data = audit_krule_to_data(r); if (unlikely(!data)) break; skb = audit_make_reply(pid, seq, AUDIT_LIST_RULES, 0, 1, @@ -1603,8 +1594,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, if (IS_ERR(entry)) return PTR_ERR(entry); - err = audit_add_rule(entry, - &audit_filter_list[entry->rule.listnr]); + err = audit_add_rule(entry); audit_log_rule_change(loginuid, sessionid, sid, "add", &entry->rule, !err); @@ -1620,8 +1610,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, if (IS_ERR(entry)) return PTR_ERR(entry); - err = audit_del_rule(entry, - &audit_filter_list[entry->rule.listnr]); + err = audit_del_rule(entry); audit_log_rule_change(loginuid, sessionid, sid, "remove", &entry->rule, !err); @@ -1634,28 +1623,29 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, return err; } -int audit_comparator(const u32 left, const u32 op, const u32 right) +int audit_comparator(u32 left, u32 op, u32 right) { switch (op) { - case AUDIT_EQUAL: + case Audit_equal: return (left == right); - case AUDIT_NOT_EQUAL: + case Audit_not_equal: return (left != right); - case AUDIT_LESS_THAN: + case Audit_lt: return (left < right); - case AUDIT_LESS_THAN_OR_EQUAL: + case Audit_le: return (left <= right); - case AUDIT_GREATER_THAN: + case Audit_gt: return (left > right); - case AUDIT_GREATER_THAN_OR_EQUAL: + case Audit_ge: return (left >= right); - case AUDIT_BIT_MASK: + case Audit_bitmask: return (left & right); - case AUDIT_BIT_TEST: + case Audit_bittest: return ((left & right) == right); + default: + BUG(); + return 0; } - BUG(); - return 0; } /* Compare given dentry name with last component in given path, @@ -1778,6 +1768,43 @@ unlock_and_return: return result; } +static int update_lsm_rule(struct audit_krule *r) +{ + struct audit_entry *entry = container_of(r, struct audit_entry, rule); + struct audit_entry *nentry; + struct audit_watch *watch; + struct audit_tree *tree; + int err = 0; + + if (!security_audit_rule_known(r)) + return 0; + + watch = r->watch; + tree = r->tree; + nentry = audit_dupe_rule(r, watch); + if (IS_ERR(nentry)) { + /* save the first error encountered for the + * return value */ + err = PTR_ERR(nentry); + audit_panic("error updating LSM filters"); + if (watch) + list_del(&r->rlist); + list_del_rcu(&entry->list); + list_del(&r->list); + } else { + if (watch) { + list_add(&nentry->rule.rlist, &watch->rules); + list_del(&r->rlist); + } else if (tree) + list_replace_init(&r->rlist, &nentry->rule.rlist); + list_replace_rcu(&entry->list, &nentry->list); + list_replace(&r->list, &nentry->rule.list); + } + call_rcu(&entry->rcu, audit_free_rule_rcu); + + return err; +} + /* This function will re-initialize the lsm_rule field of all applicable rules. * It will traverse the filter lists serarching for rules that contain LSM * specific filter fields. When such a rule is found, it is copied, the @@ -1785,45 +1812,19 @@ unlock_and_return: * updated rule. */ int audit_update_lsm_rules(void) { - struct audit_entry *entry, *n, *nentry; - struct audit_watch *watch; - struct audit_tree *tree; + struct audit_krule *r, *n; int i, err = 0; /* audit_filter_mutex synchronizes the writers */ mutex_lock(&audit_filter_mutex); for (i = 0; i < AUDIT_NR_FILTERS; i++) { - list_for_each_entry_safe(entry, n, &audit_filter_list[i], list) { - if (!security_audit_rule_known(&entry->rule)) - continue; - - watch = entry->rule.watch; - tree = entry->rule.tree; - nentry = audit_dupe_rule(&entry->rule, watch); - if (IS_ERR(nentry)) { - /* save the first error encountered for the - * return value */ - if (!err) - err = PTR_ERR(nentry); - audit_panic("error updating LSM filters"); - if (watch) - list_del(&entry->rule.rlist); - list_del_rcu(&entry->list); - } else { - if (watch) { - list_add(&nentry->rule.rlist, - &watch->rules); - list_del(&entry->rule.rlist); - } else if (tree) - list_replace_init(&entry->rule.rlist, - &nentry->rule.rlist); - list_replace_rcu(&entry->list, &nentry->list); - } - call_rcu(&entry->rcu, audit_free_rule_rcu); + list_for_each_entry_safe(r, n, &audit_rules_list[i], list) { + int res = update_lsm_rule(r); + if (!err) + err = res; } } - mutex_unlock(&audit_filter_mutex); return err; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 2a3f0af..8cbddff 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -65,6 +65,7 @@ #include <linux/highmem.h> #include <linux/syscalls.h> #include <linux/inotify.h> +#include <linux/capability.h> #include "audit.h" @@ -84,6 +85,15 @@ int audit_n_rules; /* determines whether we collect data for signals sent */ int audit_signals; +struct audit_cap_data { + kernel_cap_t permitted; + kernel_cap_t inheritable; + union { + unsigned int fE; /* effective bit of a file capability */ + kernel_cap_t effective; /* effective set of a process */ + }; +}; + /* When fs/namei.c:getname() is called, we store the pointer in name and * we don't let putname() free it (instead we free all of the saved * pointers at syscall exit time). @@ -100,6 +110,8 @@ struct audit_names { gid_t gid; dev_t rdev; u32 osid; + struct audit_cap_data fcap; + unsigned int fcap_ver; }; struct audit_aux_data { @@ -112,43 +124,6 @@ struct audit_aux_data { /* Number of target pids per aux struct. */ #define AUDIT_AUX_PIDS 16 -struct audit_aux_data_mq_open { - struct audit_aux_data d; - int oflag; - mode_t mode; - struct mq_attr attr; -}; - -struct audit_aux_data_mq_sendrecv { - struct audit_aux_data d; - mqd_t mqdes; - size_t msg_len; - unsigned int msg_prio; - struct timespec abs_timeout; -}; - -struct audit_aux_data_mq_notify { - struct audit_aux_data d; - mqd_t mqdes; - struct sigevent notification; -}; - -struct audit_aux_data_mq_getsetattr { - struct audit_aux_data d; - mqd_t mqdes; - struct mq_attr mqstat; -}; - -struct audit_aux_data_ipcctl { - struct audit_aux_data d; - struct ipc_perm p; - unsigned long qbytes; - uid_t uid; - gid_t gid; - mode_t mode; - u32 osid; -}; - struct audit_aux_data_execve { struct audit_aux_data d; int argc; @@ -156,23 +131,6 @@ struct audit_aux_data_execve { struct mm_struct *mm; }; -struct audit_aux_data_socketcall { - struct audit_aux_data d; - int nargs; - unsigned long args[0]; -}; - -struct audit_aux_data_sockaddr { - struct audit_aux_data d; - int len; - char a[0]; -}; - -struct audit_aux_data_fd_pair { - struct audit_aux_data d; - int fd[2]; -}; - struct audit_aux_data_pids { struct audit_aux_data d; pid_t target_pid[AUDIT_AUX_PIDS]; @@ -184,6 +142,20 @@ struct audit_aux_data_pids { int pid_count; }; +struct audit_aux_data_bprm_fcaps { + struct audit_aux_data d; + struct audit_cap_data fcap; + unsigned int fcap_ver; + struct audit_cap_data old_pcap; + struct audit_cap_data new_pcap; +}; + +struct audit_aux_data_capset { + struct audit_aux_data d; + pid_t pid; + struct audit_cap_data cap; +}; + struct audit_tree_refs { struct audit_tree_refs *next; struct audit_chunk *c[31]; @@ -193,14 +165,14 @@ struct audit_tree_refs { struct audit_context { int dummy; /* must be the first element */ int in_syscall; /* 1 if task is in a syscall */ - enum audit_state state; + enum audit_state state, current_state; unsigned int serial; /* serial number for record */ struct timespec ctime; /* time of syscall entry */ int major; /* syscall number */ unsigned long argv[4]; /* syscall arguments */ int return_valid; /* return code is valid */ long return_code;/* syscall return code */ - int auditable; /* 1 if record should be written */ + u64 prio; int name_count; struct audit_names names[AUDIT_NAMES]; char * filterkey; /* key for rule that triggered record */ @@ -208,7 +180,8 @@ struct audit_context { struct audit_context *previous; /* For nested syscalls */ struct audit_aux_data *aux; struct audit_aux_data *aux_pids; - + struct sockaddr_storage *sockaddr; + size_t sockaddr_len; /* Save things to print about task_struct */ pid_t pid, ppid; uid_t uid, euid, suid, fsuid; @@ -226,6 +199,49 @@ struct audit_context { struct audit_tree_refs *trees, *first_trees; int tree_count; + int type; + union { + struct { + int nargs; + long args[6]; + } socketcall; + struct { + uid_t uid; + gid_t gid; + mode_t mode; + u32 osid; + int has_perm; + uid_t perm_uid; + gid_t perm_gid; + mode_t perm_mode; + unsigned long qbytes; + } ipc; + struct { + mqd_t mqdes; + struct mq_attr mqstat; + } mq_getsetattr; + struct { + mqd_t mqdes; + int sigev_signo; + } mq_notify; + struct { + mqd_t mqdes; + size_t msg_len; + unsigned int msg_prio; + struct timespec abs_timeout; + } mq_sendrecv; + struct { + int oflag; + mode_t mode; + struct mq_attr attr; + } mq_open; + struct { + pid_t pid; + struct audit_cap_data cap; + } capset; + }; + int fds[2]; + #if AUDIT_DEBUG int put_count; int ino_count; @@ -421,6 +437,7 @@ static int audit_filter_rules(struct task_struct *tsk, struct audit_names *name, enum audit_state *state) { + const struct cred *cred = get_task_cred(tsk); int i, j, need_sid = 1; u32 sid; @@ -440,28 +457,28 @@ static int audit_filter_rules(struct task_struct *tsk, } break; case AUDIT_UID: - result = audit_comparator(tsk->uid, f->op, f->val); + result = audit_comparator(cred->uid, f->op, f->val); break; case AUDIT_EUID: - result = audit_comparator(tsk->euid, f->op, f->val); + result = audit_comparator(cred->euid, f->op, f->val); break; case AUDIT_SUID: - result = audit_comparator(tsk->suid, f->op, f->val); + result = audit_comparator(cred->suid, f->op, f->val); break; case AUDIT_FSUID: - result = audit_comparator(tsk->fsuid, f->op, f->val); + result = audit_comparator(cred->fsuid, f->op, f->val); break; case AUDIT_GID: - result = audit_comparator(tsk->gid, f->op, f->val); + result = audit_comparator(cred->gid, f->op, f->val); break; case AUDIT_EGID: - result = audit_comparator(tsk->egid, f->op, f->val); + result = audit_comparator(cred->egid, f->op, f->val); break; case AUDIT_SGID: - result = audit_comparator(tsk->sgid, f->op, f->val); + result = audit_comparator(cred->sgid, f->op, f->val); break; case AUDIT_FSGID: - result = audit_comparator(tsk->fsgid, f->op, f->val); + result = audit_comparator(cred->fsgid, f->op, f->val); break; case AUDIT_PERS: result = audit_comparator(tsk->personality, f->op, f->val); @@ -581,19 +598,12 @@ static int audit_filter_rules(struct task_struct *tsk, } } /* Find ipc objects that match */ - if (ctx) { - struct audit_aux_data *aux; - for (aux = ctx->aux; aux; - aux = aux->next) { - if (aux->type == AUDIT_IPC) { - struct audit_aux_data_ipcctl *axi = (void *)aux; - if (security_audit_rule_match(axi->osid, f->type, f->op, f->lsm_rule, ctx)) { - ++result; - break; - } - } - } - } + if (!ctx || ctx->type != AUDIT_IPC) + break; + if (security_audit_rule_match(ctx->ipc.osid, + f->type, f->op, + f->lsm_rule, ctx)) + ++result; } break; case AUDIT_ARG0: @@ -615,15 +625,26 @@ static int audit_filter_rules(struct task_struct *tsk, break; } - if (!result) + if (!result) { + put_cred(cred); return 0; + } + } + + if (ctx) { + if (rule->prio <= ctx->prio) + return 0; + if (rule->filterkey) { + kfree(ctx->filterkey); + ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC); + } + ctx->prio = rule->prio; } - if (rule->filterkey && ctx) - ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC); switch (rule->action) { case AUDIT_NEVER: *state = AUDIT_DISABLED; break; case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; } + put_cred(cred); return 1; } @@ -631,7 +652,7 @@ static int audit_filter_rules(struct task_struct *tsk, * completely disabled for this task. Since we only have the task * structure at this point, we can only check uid and gid. */ -static enum audit_state audit_filter_task(struct task_struct *tsk) +static enum audit_state audit_filter_task(struct task_struct *tsk, char **key) { struct audit_entry *e; enum audit_state state; @@ -639,6 +660,8 @@ static enum audit_state audit_filter_task(struct task_struct *tsk) rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) { if (audit_filter_rules(tsk, &e->rule, NULL, NULL, &state)) { + if (state == AUDIT_RECORD_CONTEXT) + *key = kstrdup(e->rule.filterkey, GFP_ATOMIC); rcu_read_unlock(); return state; } @@ -672,6 +695,7 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk, audit_filter_rules(tsk, &e->rule, ctx, NULL, &state)) { rcu_read_unlock(); + ctx->current_state = state; return state; } } @@ -685,15 +709,14 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk, * buckets applicable to the inode numbers in audit_names[]. * Regarding audit_state, same rules apply as for audit_filter_syscall(). */ -enum audit_state audit_filter_inodes(struct task_struct *tsk, - struct audit_context *ctx) +void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx) { int i; struct audit_entry *e; enum audit_state state; if (audit_pid && tsk->tgid == audit_pid) - return AUDIT_DISABLED; + return; rcu_read_lock(); for (i = 0; i < ctx->name_count; i++) { @@ -710,17 +733,20 @@ enum audit_state audit_filter_inodes(struct task_struct *tsk, if ((e->rule.mask[word] & bit) == bit && audit_filter_rules(tsk, &e->rule, ctx, n, &state)) { rcu_read_unlock(); - return state; + ctx->current_state = state; + return; } } } rcu_read_unlock(); - return AUDIT_BUILD_CONTEXT; } -void audit_set_auditable(struct audit_context *ctx) +static void audit_set_auditable(struct audit_context *ctx) { - ctx->auditable = 1; + if (!ctx->prio) { + ctx->prio = 1; + ctx->current_state = AUDIT_RECORD_CONTEXT; + } } static inline struct audit_context *audit_get_context(struct task_struct *tsk, @@ -751,23 +777,11 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk, else context->return_code = return_code; - if (context->in_syscall && !context->dummy && !context->auditable) { - enum audit_state state; - - state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]); - if (state == AUDIT_RECORD_CONTEXT) { - context->auditable = 1; - goto get_context; - } - - state = audit_filter_inodes(tsk, context); - if (state == AUDIT_RECORD_CONTEXT) - context->auditable = 1; - + if (context->in_syscall && !context->dummy) { + audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]); + audit_filter_inodes(tsk, context); } -get_context: - tsk->audit_context = NULL; return context; } @@ -777,8 +791,7 @@ static inline void audit_free_names(struct audit_context *context) int i; #if AUDIT_DEBUG == 2 - if (context->auditable - ||context->put_count + context->ino_count != context->name_count) { + if (context->put_count + context->ino_count != context->name_count) { printk(KERN_ERR "%s:%d(:%d): major=%d in_syscall=%d" " name_count=%d put_count=%d" " ino_count=%d [NOT freeing]\n", @@ -829,6 +842,7 @@ static inline void audit_zero_context(struct audit_context *context, { memset(context, 0, sizeof(*context)); context->state = state; + context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; } static inline struct audit_context *audit_alloc_context(enum audit_state state) @@ -854,18 +868,21 @@ int audit_alloc(struct task_struct *tsk) { struct audit_context *context; enum audit_state state; + char *key = NULL; if (likely(!audit_ever_enabled)) return 0; /* Return if not auditing. */ - state = audit_filter_task(tsk); + state = audit_filter_task(tsk, &key); if (likely(state == AUDIT_DISABLED)) return 0; if (!(context = audit_alloc_context(state))) { + kfree(key); audit_log_lost("out of memory in audit_alloc"); return -ENOMEM; } + context->filterkey = key; tsk->audit_context = context; set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT); @@ -891,6 +908,7 @@ static inline void audit_free_context(struct audit_context *context) free_tree_refs(context); audit_free_aux(context); kfree(context->filterkey); + kfree(context->sockaddr); kfree(context); context = previous; } while (context); @@ -1171,8 +1189,129 @@ static void audit_log_execve_info(struct audit_context *context, kfree(buf); } +static void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) +{ + int i; + + audit_log_format(ab, " %s=", prefix); + CAP_FOR_EACH_U32(i) { + audit_log_format(ab, "%08x", cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]); + } +} + +static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) +{ + kernel_cap_t *perm = &name->fcap.permitted; + kernel_cap_t *inh = &name->fcap.inheritable; + int log = 0; + + if (!cap_isclear(*perm)) { + audit_log_cap(ab, "cap_fp", perm); + log = 1; + } + if (!cap_isclear(*inh)) { + audit_log_cap(ab, "cap_fi", inh); + log = 1; + } + + if (log) + audit_log_format(ab, " cap_fe=%d cap_fver=%x", name->fcap.fE, name->fcap_ver); +} + +static void show_special(struct audit_context *context, int *call_panic) +{ + struct audit_buffer *ab; + int i; + + ab = audit_log_start(context, GFP_KERNEL, context->type); + if (!ab) + return; + + switch (context->type) { + case AUDIT_SOCKETCALL: { + int nargs = context->socketcall.nargs; + audit_log_format(ab, "nargs=%d", nargs); + for (i = 0; i < nargs; i++) + audit_log_format(ab, " a%d=%lx", i, + context->socketcall.args[i]); + break; } + case AUDIT_IPC: { + u32 osid = context->ipc.osid; + + audit_log_format(ab, "ouid=%u ogid=%u mode=%#o", + context->ipc.uid, context->ipc.gid, context->ipc.mode); + if (osid) { + char *ctx = NULL; + u32 len; + if (security_secid_to_secctx(osid, &ctx, &len)) { + audit_log_format(ab, " osid=%u", osid); + *call_panic = 1; + } else { + audit_log_format(ab, " obj=%s", ctx); + security_release_secctx(ctx, len); + } + } + if (context->ipc.has_perm) { + audit_log_end(ab); + ab = audit_log_start(context, GFP_KERNEL, + AUDIT_IPC_SET_PERM); + audit_log_format(ab, + "qbytes=%lx ouid=%u ogid=%u mode=%#o", + context->ipc.qbytes, + context->ipc.perm_uid, + context->ipc.perm_gid, + context->ipc.perm_mode); + if (!ab) + return; + } + break; } + case AUDIT_MQ_OPEN: { + audit_log_format(ab, + "oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld " + "mq_msgsize=%ld mq_curmsgs=%ld", + context->mq_open.oflag, context->mq_open.mode, + context->mq_open.attr.mq_flags, + context->mq_open.attr.mq_maxmsg, + context->mq_open.attr.mq_msgsize, + context->mq_open.attr.mq_curmsgs); + break; } + case AUDIT_MQ_SENDRECV: { + audit_log_format(ab, + "mqdes=%d msg_len=%zd msg_prio=%u " + "abs_timeout_sec=%ld abs_timeout_nsec=%ld", + context->mq_sendrecv.mqdes, + context->mq_sendrecv.msg_len, + context->mq_sendrecv.msg_prio, + context->mq_sendrecv.abs_timeout.tv_sec, + context->mq_sendrecv.abs_timeout.tv_nsec); + break; } + case AUDIT_MQ_NOTIFY: { + audit_log_format(ab, "mqdes=%d sigev_signo=%d", + context->mq_notify.mqdes, + context->mq_notify.sigev_signo); + break; } + case AUDIT_MQ_GETSETATTR: { + struct mq_attr *attr = &context->mq_getsetattr.mqstat; + audit_log_format(ab, + "mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld " + "mq_curmsgs=%ld ", + context->mq_getsetattr.mqdes, + attr->mq_flags, attr->mq_maxmsg, + attr->mq_msgsize, attr->mq_curmsgs); + break; } + case AUDIT_CAPSET: { + audit_log_format(ab, "pid=%d", context->capset.pid); + audit_log_cap(ab, "cap_pi", &context->capset.cap.inheritable); + audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted); + audit_log_cap(ab, "cap_pe", &context->capset.cap.effective); + break; } + } + audit_log_end(ab); +} + static void audit_log_exit(struct audit_context *context, struct task_struct *tsk) { + const struct cred *cred; int i, call_panic = 0; struct audit_buffer *ab; struct audit_aux_data *aux; @@ -1182,14 +1321,15 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts context->pid = tsk->pid; if (!context->ppid) context->ppid = sys_getppid(); - context->uid = tsk->uid; - context->gid = tsk->gid; - context->euid = tsk->euid; - context->suid = tsk->suid; - context->fsuid = tsk->fsuid; - context->egid = tsk->egid; - context->sgid = tsk->sgid; - context->fsgid = tsk->fsgid; + cred = current_cred(); + context->uid = cred->uid; + context->gid = cred->gid; + context->euid = cred->euid; + context->suid = cred->suid; + context->fsuid = cred->fsuid; + context->egid = cred->egid; + context->sgid = cred->sgid; + context->fsgid = cred->fsgid; context->personality = tsk->personality; ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL); @@ -1246,96 +1386,50 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts continue; /* audit_panic has been called */ switch (aux->type) { - case AUDIT_MQ_OPEN: { - struct audit_aux_data_mq_open *axi = (void *)aux; - audit_log_format(ab, - "oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld " - "mq_msgsize=%ld mq_curmsgs=%ld", - axi->oflag, axi->mode, axi->attr.mq_flags, - axi->attr.mq_maxmsg, axi->attr.mq_msgsize, - axi->attr.mq_curmsgs); - break; } - - case AUDIT_MQ_SENDRECV: { - struct audit_aux_data_mq_sendrecv *axi = (void *)aux; - audit_log_format(ab, - "mqdes=%d msg_len=%zd msg_prio=%u " - "abs_timeout_sec=%ld abs_timeout_nsec=%ld", - axi->mqdes, axi->msg_len, axi->msg_prio, - axi->abs_timeout.tv_sec, axi->abs_timeout.tv_nsec); - break; } - - case AUDIT_MQ_NOTIFY: { - struct audit_aux_data_mq_notify *axi = (void *)aux; - audit_log_format(ab, - "mqdes=%d sigev_signo=%d", - axi->mqdes, - axi->notification.sigev_signo); - break; } - - case AUDIT_MQ_GETSETATTR: { - struct audit_aux_data_mq_getsetattr *axi = (void *)aux; - audit_log_format(ab, - "mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld " - "mq_curmsgs=%ld ", - axi->mqdes, - axi->mqstat.mq_flags, axi->mqstat.mq_maxmsg, - axi->mqstat.mq_msgsize, axi->mqstat.mq_curmsgs); - break; } - - case AUDIT_IPC: { - struct audit_aux_data_ipcctl *axi = (void *)aux; - audit_log_format(ab, - "ouid=%u ogid=%u mode=%#o", - axi->uid, axi->gid, axi->mode); - if (axi->osid != 0) { - char *ctx = NULL; - u32 len; - if (security_secid_to_secctx( - axi->osid, &ctx, &len)) { - audit_log_format(ab, " osid=%u", - axi->osid); - call_panic = 1; - } else { - audit_log_format(ab, " obj=%s", ctx); - security_release_secctx(ctx, len); - } - } - break; } - - case AUDIT_IPC_SET_PERM: { - struct audit_aux_data_ipcctl *axi = (void *)aux; - audit_log_format(ab, - "qbytes=%lx ouid=%u ogid=%u mode=%#o", - axi->qbytes, axi->uid, axi->gid, axi->mode); - break; } case AUDIT_EXECVE: { struct audit_aux_data_execve *axi = (void *)aux; audit_log_execve_info(context, &ab, axi); break; } - case AUDIT_SOCKETCALL: { - struct audit_aux_data_socketcall *axs = (void *)aux; - audit_log_format(ab, "nargs=%d", axs->nargs); - for (i=0; i<axs->nargs; i++) - audit_log_format(ab, " a%d=%lx", i, axs->args[i]); + case AUDIT_BPRM_FCAPS: { + struct audit_aux_data_bprm_fcaps *axs = (void *)aux; + audit_log_format(ab, "fver=%x", axs->fcap_ver); + audit_log_cap(ab, "fp", &axs->fcap.permitted); + audit_log_cap(ab, "fi", &axs->fcap.inheritable); + audit_log_format(ab, " fe=%d", axs->fcap.fE); + audit_log_cap(ab, "old_pp", &axs->old_pcap.permitted); + audit_log_cap(ab, "old_pi", &axs->old_pcap.inheritable); + audit_log_cap(ab, "old_pe", &axs->old_pcap.effective); + audit_log_cap(ab, "new_pp", &axs->new_pcap.permitted); + audit_log_cap(ab, "new_pi", &axs->new_pcap.inheritable); + audit_log_cap(ab, "new_pe", &axs->new_pcap.effective); break; } - case AUDIT_SOCKADDR: { - struct audit_aux_data_sockaddr *axs = (void *)aux; + } + audit_log_end(ab); + } - audit_log_format(ab, "saddr="); - audit_log_n_hex(ab, axs->a, axs->len); - break; } + if (context->type) + show_special(context, &call_panic); - case AUDIT_FD_PAIR: { - struct audit_aux_data_fd_pair *axs = (void *)aux; - audit_log_format(ab, "fd0=%d fd1=%d", axs->fd[0], axs->fd[1]); - break; } + if (context->fds[0] >= 0) { + ab = audit_log_start(context, GFP_KERNEL, AUDIT_FD_PAIR); + if (ab) { + audit_log_format(ab, "fd0=%d fd1=%d", + context->fds[0], context->fds[1]); + audit_log_end(ab); + } + } + if (context->sockaddr_len) { + ab = audit_log_start(context, GFP_KERNEL, AUDIT_SOCKADDR); + if (ab) { + audit_log_format(ab, "saddr="); + audit_log_n_hex(ab, (void *)context->sockaddr, + context->sockaddr_len); + audit_log_end(ab); } - audit_log_end(ab); } for (aux = context->aux_pids; aux; aux = aux->next) { @@ -1421,6 +1515,8 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts } } + audit_log_fcaps(ab, n); + audit_log_end(ab); } @@ -1451,7 +1547,7 @@ void audit_free(struct task_struct *tsk) * We use GFP_ATOMIC here because we might be doing this * in the context of the idle thread */ /* that can happen only if we are called from do_exit() */ - if (context->in_syscall && context->auditable) + if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT) audit_log_exit(context, tsk); audit_free_context(context); @@ -1535,15 +1631,17 @@ void audit_syscall_entry(int arch, int major, state = context->state; context->dummy = !audit_n_rules; - if (!context->dummy && (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT)) + if (!context->dummy && state == AUDIT_BUILD_CONTEXT) { + context->prio = 0; state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]); + } if (likely(state == AUDIT_DISABLED)) return; context->serial = 0; context->ctime = CURRENT_TIME; context->in_syscall = 1; - context->auditable = !!(state == AUDIT_RECORD_CONTEXT); + context->current_state = state; context->ppid = 0; } @@ -1551,17 +1649,20 @@ void audit_finish_fork(struct task_struct *child) { struct audit_context *ctx = current->audit_context; struct audit_context *p = child->audit_context; - if (!p || !ctx || !ctx->auditable) + if (!p || !ctx) + return; + if (!ctx->in_syscall || ctx->current_state != AUDIT_RECORD_CONTEXT) return; p->arch = ctx->arch; p->major = ctx->major; memcpy(p->argv, ctx->argv, sizeof(ctx->argv)); p->ctime = ctx->ctime; p->dummy = ctx->dummy; - p->auditable = ctx->auditable; p->in_syscall = ctx->in_syscall; p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL); p->ppid = current->pid; + p->prio = ctx->prio; + p->current_state = ctx->current_state; } /** @@ -1585,11 +1686,11 @@ void audit_syscall_exit(int valid, long return_code) if (likely(!context)) return; - if (context->in_syscall && context->auditable) + if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT) audit_log_exit(context, tsk); context->in_syscall = 0; - context->auditable = 0; + context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; if (context->previous) { struct audit_context *new_context = context->previous; @@ -1604,8 +1705,13 @@ void audit_syscall_exit(int valid, long return_code) context->aux_pids = NULL; context->target_pid = 0; context->target_sid = 0; - kfree(context->filterkey); - context->filterkey = NULL; + context->sockaddr_len = 0; + context->type = 0; + context->fds[0] = -1; + if (context->state != AUDIT_RECORD_CONTEXT) { + kfree(context->filterkey); + context->filterkey = NULL; + } tsk->audit_context = context; } } @@ -1802,8 +1908,36 @@ static int audit_inc_name_count(struct audit_context *context, return 0; } + +static inline int audit_copy_fcaps(struct audit_names *name, const struct dentry *dentry) +{ + struct cpu_vfs_cap_data caps; + int rc; + + memset(&name->fcap.permitted, 0, sizeof(kernel_cap_t)); + memset(&name->fcap.inheritable, 0, sizeof(kernel_cap_t)); + name->fcap.fE = 0; + name->fcap_ver = 0; + + if (!dentry) + return 0; + + rc = get_vfs_caps_from_disk(dentry, &caps); + if (rc) + return rc; + + name->fcap.permitted = caps.permitted; + name->fcap.inheritable = caps.inheritable; + name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT; + + return 0; +} + + /* Copy inode data into an audit_names. */ -static void audit_copy_inode(struct audit_names *name, const struct inode *inode) +static void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, + const struct inode *inode) { name->ino = inode->i_ino; name->dev = inode->i_sb->s_dev; @@ -1812,6 +1946,7 @@ static void audit_copy_inode(struct audit_names *name, const struct inode *inode name->gid = inode->i_gid; name->rdev = inode->i_rdev; security_inode_getsecid(inode, &name->osid); + audit_copy_fcaps(name, dentry); } /** @@ -1846,7 +1981,7 @@ void __audit_inode(const char *name, const struct dentry *dentry) context->names[idx].name = NULL; } handle_path(dentry); - audit_copy_inode(&context->names[idx], inode); + audit_copy_inode(&context->names[idx], dentry, inode); } /** @@ -1907,7 +2042,7 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry, if (!strcmp(dname, n->name) || !audit_compare_dname_path(dname, n->name, &dirlen)) { if (inode) - audit_copy_inode(n, inode); + audit_copy_inode(n, NULL, inode); else n->ino = (unsigned long)-1; found_child = n->name; @@ -1921,7 +2056,7 @@ add_names: return; idx = context->name_count - 1; context->names[idx].name = NULL; - audit_copy_inode(&context->names[idx], parent); + audit_copy_inode(&context->names[idx], NULL, parent); } if (!found_child) { @@ -1942,7 +2077,7 @@ add_names: } if (inode) - audit_copy_inode(&context->names[idx], inode); + audit_copy_inode(&context->names[idx], NULL, inode); else context->names[idx].ino = (unsigned long)-1; } @@ -1967,7 +2102,10 @@ int auditsc_get_stamp(struct audit_context *ctx, t->tv_sec = ctx->ctime.tv_sec; t->tv_nsec = ctx->ctime.tv_nsec; *serial = ctx->serial; - ctx->auditable = 1; + if (!ctx->prio) { + ctx->prio = 1; + ctx->current_state = AUDIT_RECORD_CONTEXT; + } return 1; } @@ -1996,7 +2134,7 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid) audit_log_format(ab, "login pid=%d uid=%u " "old auid=%u new auid=%u" " old ses=%u new ses=%u", - task->pid, task->uid, + task->pid, task_uid(task), task->loginuid, loginuid, task->sessionid, sessionid); audit_log_end(ab); @@ -2013,132 +2151,46 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid) * @mode: mode bits * @u_attr: queue attributes * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr) +void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr) { - struct audit_aux_data_mq_open *ax; struct audit_context *context = current->audit_context; - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - if (u_attr != NULL) { - if (copy_from_user(&ax->attr, u_attr, sizeof(ax->attr))) { - kfree(ax); - return -EFAULT; - } - } else - memset(&ax->attr, 0, sizeof(ax->attr)); + if (attr) + memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr)); + else + memset(&context->mq_open.attr, 0, sizeof(struct mq_attr)); - ax->oflag = oflag; - ax->mode = mode; + context->mq_open.oflag = oflag; + context->mq_open.mode = mode; - ax->d.type = AUDIT_MQ_OPEN; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->type = AUDIT_MQ_OPEN; } /** - * __audit_mq_timedsend - record audit data for a POSIX MQ timed send + * __audit_mq_sendrecv - record audit data for a POSIX MQ timed send/receive * @mqdes: MQ descriptor * @msg_len: Message length * @msg_prio: Message priority - * @u_abs_timeout: Message timeout in absolute time + * @abs_timeout: Message timeout in absolute time * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, - const struct timespec __user *u_abs_timeout) +void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, + const struct timespec *abs_timeout) { - struct audit_aux_data_mq_sendrecv *ax; struct audit_context *context = current->audit_context; + struct timespec *p = &context->mq_sendrecv.abs_timeout; - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - if (u_abs_timeout != NULL) { - if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) { - kfree(ax); - return -EFAULT; - } - } else - memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout)); - - ax->mqdes = mqdes; - ax->msg_len = msg_len; - ax->msg_prio = msg_prio; - - ax->d.type = AUDIT_MQ_SENDRECV; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; -} - -/** - * __audit_mq_timedreceive - record audit data for a POSIX MQ timed receive - * @mqdes: MQ descriptor - * @msg_len: Message length - * @u_msg_prio: Message priority - * @u_abs_timeout: Message timeout in absolute time - * - * Returns 0 for success or NULL context or < 0 on error. - */ -int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, - unsigned int __user *u_msg_prio, - const struct timespec __user *u_abs_timeout) -{ - struct audit_aux_data_mq_sendrecv *ax; - struct audit_context *context = current->audit_context; - - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - if (u_msg_prio != NULL) { - if (get_user(ax->msg_prio, u_msg_prio)) { - kfree(ax); - return -EFAULT; - } - } else - ax->msg_prio = 0; - - if (u_abs_timeout != NULL) { - if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) { - kfree(ax); - return -EFAULT; - } - } else - memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout)); + if (abs_timeout) + memcpy(p, abs_timeout, sizeof(struct timespec)); + else + memset(p, 0, sizeof(struct timespec)); - ax->mqdes = mqdes; - ax->msg_len = msg_len; + context->mq_sendrecv.mqdes = mqdes; + context->mq_sendrecv.msg_len = msg_len; + context->mq_sendrecv.msg_prio = msg_prio; - ax->d.type = AUDIT_MQ_SENDRECV; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->type = AUDIT_MQ_SENDRECV; } /** @@ -2146,38 +2198,19 @@ int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, * @mqdes: MQ descriptor * @u_notification: Notification event * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification) +void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { - struct audit_aux_data_mq_notify *ax; struct audit_context *context = current->audit_context; - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - if (u_notification != NULL) { - if (copy_from_user(&ax->notification, u_notification, sizeof(ax->notification))) { - kfree(ax); - return -EFAULT; - } - } else - memset(&ax->notification, 0, sizeof(ax->notification)); - - ax->mqdes = mqdes; + if (notification) + context->mq_notify.sigev_signo = notification->sigev_signo; + else + context->mq_notify.sigev_signo = 0; - ax->d.type = AUDIT_MQ_NOTIFY; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->mq_notify.mqdes = mqdes; + context->type = AUDIT_MQ_NOTIFY; } /** @@ -2185,55 +2218,29 @@ int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification) * @mqdes: MQ descriptor * @mqstat: MQ flags * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) +void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { - struct audit_aux_data_mq_getsetattr *ax; struct audit_context *context = current->audit_context; - - if (!audit_enabled) - return 0; - - if (likely(!context)) - return 0; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - ax->mqdes = mqdes; - ax->mqstat = *mqstat; - - ax->d.type = AUDIT_MQ_GETSETATTR; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->mq_getsetattr.mqdes = mqdes; + context->mq_getsetattr.mqstat = *mqstat; + context->type = AUDIT_MQ_GETSETATTR; } /** * audit_ipc_obj - record audit data for ipc object * @ipcp: ipc permissions * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_ipc_obj(struct kern_ipc_perm *ipcp) +void __audit_ipc_obj(struct kern_ipc_perm *ipcp) { - struct audit_aux_data_ipcctl *ax; struct audit_context *context = current->audit_context; - - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - ax->uid = ipcp->uid; - ax->gid = ipcp->gid; - ax->mode = ipcp->mode; - security_ipc_getsecid(ipcp, &ax->osid); - ax->d.type = AUDIT_IPC; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->ipc.uid = ipcp->uid; + context->ipc.gid = ipcp->gid; + context->ipc.mode = ipcp->mode; + context->ipc.has_perm = 0; + security_ipc_getsecid(ipcp, &context->ipc.osid); + context->type = AUDIT_IPC; } /** @@ -2243,26 +2250,17 @@ int __audit_ipc_obj(struct kern_ipc_perm *ipcp) * @gid: msgq group id * @mode: msgq mode (permissions) * - * Returns 0 for success or NULL context or < 0 on error. + * Called only after audit_ipc_obj(). */ -int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) +void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) { - struct audit_aux_data_ipcctl *ax; struct audit_context *context = current->audit_context; - ax = kmalloc(sizeof(*ax), GFP_ATOMIC); - if (!ax) - return -ENOMEM; - - ax->qbytes = qbytes; - ax->uid = uid; - ax->gid = gid; - ax->mode = mode; - - ax->d.type = AUDIT_IPC_SET_PERM; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->ipc.qbytes = qbytes; + context->ipc.perm_uid = uid; + context->ipc.perm_gid = gid; + context->ipc.perm_mode = mode; + context->ipc.has_perm = 1; } int audit_bprm(struct linux_binprm *bprm) @@ -2292,27 +2290,17 @@ int audit_bprm(struct linux_binprm *bprm) * @nargs: number of args * @args: args array * - * Returns 0 for success or NULL context or < 0 on error. */ -int audit_socketcall(int nargs, unsigned long *args) +void audit_socketcall(int nargs, unsigned long *args) { - struct audit_aux_data_socketcall *ax; struct audit_context *context = current->audit_context; if (likely(!context || context->dummy)) - return 0; - - ax = kmalloc(sizeof(*ax) + nargs * sizeof(unsigned long), GFP_KERNEL); - if (!ax) - return -ENOMEM; - - ax->nargs = nargs; - memcpy(ax->args, args, nargs * sizeof(unsigned long)); + return; - ax->d.type = AUDIT_SOCKETCALL; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->type = AUDIT_SOCKETCALL; + context->socketcall.nargs = nargs; + memcpy(context->socketcall.args, args, nargs * sizeof(unsigned long)); } /** @@ -2320,29 +2308,12 @@ int audit_socketcall(int nargs, unsigned long *args) * @fd1: the first file descriptor * @fd2: the second file descriptor * - * Returns 0 for success or NULL context or < 0 on error. */ -int __audit_fd_pair(int fd1, int fd2) +void __audit_fd_pair(int fd1, int fd2) { struct audit_context *context = current->audit_context; - struct audit_aux_data_fd_pair *ax; - - if (likely(!context)) { - return 0; - } - - ax = kmalloc(sizeof(*ax), GFP_KERNEL); - if (!ax) { - return -ENOMEM; - } - - ax->fd[0] = fd1; - ax->fd[1] = fd2; - - ax->d.type = AUDIT_FD_PAIR; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->fds[0] = fd1; + context->fds[1] = fd2; } /** @@ -2354,22 +2325,20 @@ int __audit_fd_pair(int fd1, int fd2) */ int audit_sockaddr(int len, void *a) { - struct audit_aux_data_sockaddr *ax; struct audit_context *context = current->audit_context; if (likely(!context || context->dummy)) return 0; - ax = kmalloc(sizeof(*ax) + len, GFP_KERNEL); - if (!ax) - return -ENOMEM; - - ax->len = len; - memcpy(ax->a, a, len); + if (!context->sockaddr) { + void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL); + if (!p) + return -ENOMEM; + context->sockaddr = p; + } - ax->d.type = AUDIT_SOCKADDR; - ax->d.next = context->aux; - context->aux = (void *)ax; + context->sockaddr_len = len; + memcpy(context->sockaddr, a, len); return 0; } @@ -2379,7 +2348,7 @@ void __audit_ptrace(struct task_struct *t) context->target_pid = t->pid; context->target_auid = audit_get_loginuid(t); - context->target_uid = t->uid; + context->target_uid = task_uid(t); context->target_sessionid = audit_get_sessionid(t); security_task_getsecid(t, &context->target_sid); memcpy(context->target_comm, t->comm, TASK_COMM_LEN); @@ -2398,6 +2367,7 @@ int __audit_signal_info(int sig, struct task_struct *t) struct audit_aux_data_pids *axp; struct task_struct *tsk = current; struct audit_context *ctx = tsk->audit_context; + uid_t uid = current_uid(), t_uid = task_uid(t); if (audit_pid && t->tgid == audit_pid) { if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) { @@ -2405,7 +2375,7 @@ int __audit_signal_info(int sig, struct task_struct *t) if (tsk->loginuid != -1) audit_sig_uid = tsk->loginuid; else - audit_sig_uid = tsk->uid; + audit_sig_uid = uid; security_task_getsecid(tsk, &audit_sig_sid); } if (!audit_signals || audit_dummy_context()) @@ -2417,7 +2387,7 @@ int __audit_signal_info(int sig, struct task_struct *t) if (!ctx->target_pid) { ctx->target_pid = t->tgid; ctx->target_auid = audit_get_loginuid(t); - ctx->target_uid = t->uid; + ctx->target_uid = t_uid; ctx->target_sessionid = audit_get_sessionid(t); security_task_getsecid(t, &ctx->target_sid); memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN); @@ -2438,7 +2408,7 @@ int __audit_signal_info(int sig, struct task_struct *t) axp->target_pid[axp->pid_count] = t->tgid; axp->target_auid[axp->pid_count] = audit_get_loginuid(t); - axp->target_uid[axp->pid_count] = t->uid; + axp->target_uid[axp->pid_count] = t_uid; axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); security_task_getsecid(t, &axp->target_sid[axp->pid_count]); memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN); @@ -2448,6 +2418,72 @@ int __audit_signal_info(int sig, struct task_struct *t) } /** + * __audit_log_bprm_fcaps - store information about a loading bprm and relevant fcaps + * @bprm: pointer to the bprm being processed + * @new: the proposed new credentials + * @old: the old credentials + * + * Simply check if the proc already has the caps given by the file and if not + * store the priv escalation info for later auditing at the end of the syscall + * + * -Eric + */ +int __audit_log_bprm_fcaps(struct linux_binprm *bprm, + const struct cred *new, const struct cred *old) +{ + struct audit_aux_data_bprm_fcaps *ax; + struct audit_context *context = current->audit_context; + struct cpu_vfs_cap_data vcaps; + struct dentry *dentry; + + ax = kmalloc(sizeof(*ax), GFP_KERNEL); + if (!ax) + return -ENOMEM; + + ax->d.type = AUDIT_BPRM_FCAPS; + ax->d.next = context->aux; + context->aux = (void *)ax; + + dentry = dget(bprm->file->f_dentry); + get_vfs_caps_from_disk(dentry, &vcaps); + dput(dentry); + + ax->fcap.permitted = vcaps.permitted; + ax->fcap.inheritable = vcaps.inheritable; + ax->fcap.fE = !!(vcaps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + ax->fcap_ver = (vcaps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT; + + ax->old_pcap.permitted = old->cap_permitted; + ax->old_pcap.inheritable = old->cap_inheritable; + ax->old_pcap.effective = old->cap_effective; + + ax->new_pcap.permitted = new->cap_permitted; + ax->new_pcap.inheritable = new->cap_inheritable; + ax->new_pcap.effective = new->cap_effective; + return 0; +} + +/** + * __audit_log_capset - store information about the arguments to the capset syscall + * @pid: target pid of the capset call + * @new: the new credentials + * @old: the old (current) credentials + * + * Record the aguments userspace sent to sys_capset for later printing by the + * audit system if applicable + */ +void __audit_log_capset(pid_t pid, + const struct cred *new, const struct cred *old) +{ + struct audit_context *context = current->audit_context; + context->capset.pid = pid; + context->capset.cap.effective = new->cap_effective; + context->capset.cap.inheritable = new->cap_effective; + context->capset.cap.permitted = new->cap_permitted; + context->type = AUDIT_CAPSET; +} + +/** * audit_core_dumps - record information about processes that end abnormally * @signr: signal value * @@ -2458,7 +2494,8 @@ void audit_core_dumps(long signr) { struct audit_buffer *ab; u32 sid; - uid_t auid = audit_get_loginuid(current); + uid_t auid = audit_get_loginuid(current), uid; + gid_t gid; unsigned int sessionid = audit_get_sessionid(current); if (!audit_enabled) @@ -2468,8 +2505,9 @@ void audit_core_dumps(long signr) return; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); + current_uid_gid(&uid, &gid); audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u", - auid, current->uid, current->gid, sessionid); + auid, uid, gid, sessionid); security_task_getsecid(current, &sid); if (sid) { char *ctx = NULL; diff --git a/kernel/capability.c b/kernel/capability.c index 33e51e7..688926e 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -7,6 +7,7 @@ * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ +#include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/module.h> @@ -14,12 +15,7 @@ #include <linux/syscalls.h> #include <linux/pid_namespace.h> #include <asm/uaccess.h> - -/* - * This lock protects task->cap_* for all tasks including current. - * Locking rule: acquire this prior to tasklist_lock. - */ -static DEFINE_SPINLOCK(task_capability_lock); +#include "cred-internals.h" /* * Leveraged for setting/resetting capabilities @@ -33,6 +29,17 @@ EXPORT_SYMBOL(__cap_empty_set); EXPORT_SYMBOL(__cap_full_set); EXPORT_SYMBOL(__cap_init_eff_set); +#ifdef CONFIG_SECURITY_FILE_CAPABILITIES +int file_caps_enabled = 1; + +static int __init file_caps_disable(char *str) +{ + file_caps_enabled = 0; + return 1; +} +__setup("no_file_caps", file_caps_disable); +#endif + /* * More recent versions of libcap are available from: * @@ -115,167 +122,12 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) return 0; } -#ifndef CONFIG_SECURITY_FILE_CAPABILITIES - /* - * Without filesystem capability support, we nominally support one process - * setting the capabilities of another - */ -static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, - kernel_cap_t *pIp, kernel_cap_t *pPp) -{ - struct task_struct *target; - int ret; - - spin_lock(&task_capability_lock); - read_lock(&tasklist_lock); - - if (pid && pid != task_pid_vnr(current)) { - target = find_task_by_vpid(pid); - if (!target) { - ret = -ESRCH; - goto out; - } - } else - target = current; - - ret = security_capget(target, pEp, pIp, pPp); - -out: - read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); - - return ret; -} - -/* - * cap_set_pg - set capabilities for all processes in a given process - * group. We call this holding task_capability_lock and tasklist_lock. - */ -static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - struct task_struct *g, *target; - int ret = -EPERM; - int found = 0; - struct pid *pgrp; - - spin_lock(&task_capability_lock); - read_lock(&tasklist_lock); - - pgrp = find_vpid(pgrp_nr); - do_each_pid_task(pgrp, PIDTYPE_PGID, g) { - target = g; - while_each_thread(g, target) { - if (!security_capset_check(target, effective, - inheritable, permitted)) { - security_capset_set(target, effective, - inheritable, permitted); - ret = 0; - } - found = 1; - } - } while_each_pid_task(pgrp, PIDTYPE_PGID, g); - - read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); - - if (!found) - ret = 0; - return ret; -} - -/* - * cap_set_all - set capabilities for all processes other than init - * and self. We call this holding task_capability_lock and tasklist_lock. - */ -static inline int cap_set_all(kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - struct task_struct *g, *target; - int ret = -EPERM; - int found = 0; - - spin_lock(&task_capability_lock); - read_lock(&tasklist_lock); - - do_each_thread(g, target) { - if (target == current - || is_container_init(target->group_leader)) - continue; - found = 1; - if (security_capset_check(target, effective, inheritable, - permitted)) - continue; - ret = 0; - security_capset_set(target, effective, inheritable, permitted); - } while_each_thread(g, target); - - read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); - - if (!found) - ret = 0; - - return ret; -} - -/* - * Given the target pid does not refer to the current process we - * need more elaborate support... (This support is not present when - * filesystem capabilities are configured.) - */ -static inline int do_sys_capset_other_tasks(pid_t pid, kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - struct task_struct *target; - int ret; - - if (!capable(CAP_SETPCAP)) - return -EPERM; - - if (pid == -1) /* all procs other than current and init */ - return cap_set_all(effective, inheritable, permitted); - - else if (pid < 0) /* all procs in process group */ - return cap_set_pg(-pid, effective, inheritable, permitted); - - /* target != current */ - spin_lock(&task_capability_lock); - read_lock(&tasklist_lock); - - target = find_task_by_vpid(pid); - if (!target) - ret = -ESRCH; - else { - ret = security_capset_check(target, effective, inheritable, - permitted); - - /* having verified that the proposed changes are legal, - we now put them into effect. */ - if (!ret) - security_capset_set(target, effective, inheritable, - permitted); - } - - read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); - - return ret; -} - -#else /* ie., def CONFIG_SECURITY_FILE_CAPABILITIES */ - -/* - * If we have configured with filesystem capability support, then the - * only thing that can change the capabilities of the current process - * is the current process. As such, we can't be in this code at the - * same time as we are in the process of setting capabilities in this - * process. The net result is that we can limit our use of locks to - * when we are reading the caps of another process. + * The only thing that can change the capabilities of the current + * process is the current process. As such, we can't be in this code + * at the same time as we are in the process of setting capabilities + * in this process. The net result is that we can limit our use of + * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) @@ -285,7 +137,6 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, if (pid && (pid != task_pid_vnr(current))) { struct task_struct *target; - spin_lock(&task_capability_lock); read_lock(&tasklist_lock); target = find_task_by_vpid(pid); @@ -295,50 +146,12 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, ret = security_capget(target, pEp, pIp, pPp); read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } -/* - * With filesystem capability support configured, the kernel does not - * permit the changing of capabilities in one process by another - * process. (CAP_SETPCAP has much less broad semantics when configured - * this way.) - */ -static inline int do_sys_capset_other_tasks(pid_t pid, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - return -EPERM; -} - -#endif /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */ - -/* - * Atomically modify the effective capabilities returning the original - * value. No permission check is performed here - it is assumed that the - * caller is permitted to set the desired effective capabilities. - */ -kernel_cap_t cap_set_effective(const kernel_cap_t pE_new) -{ - kernel_cap_t pE_old; - - spin_lock(&task_capability_lock); - - pE_old = current->cap_effective; - current->cap_effective = pE_new; - - spin_unlock(&task_capability_lock); - - return pE_old; -} - -EXPORT_SYMBOL(cap_set_effective); - /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and @@ -366,7 +179,6 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); - if (!ret) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i; @@ -412,16 +224,14 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * - * Set capabilities for a given process, all processes, or all - * processes in a given process group. + * Set capabilities for the current process only. The ability to any other + * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * - * [pid is for the 'target' task. 'current' is the calling task.] - * - * I: any raised capabilities must be a subset of the (old current) permitted - * P: any raised capabilities must be a subset of the (old current) permitted - * E: must be set to a subset of (new target) permitted + * I: any raised capabilities must be a subset of the old permitted + * P: any raised capabilities must be a subset of the old permitted + * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ @@ -430,6 +240,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i, tocopy; kernel_cap_t inheritable, permitted, effective; + struct cred *new; int ret; pid_t pid; @@ -440,10 +251,13 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) if (get_user(pid, &header->pid)) return -EFAULT; - if (copy_from_user(&kdata, data, tocopy - * sizeof(struct __user_cap_data_struct))) { + /* may only affect current now */ + if (pid != 0 && pid != task_pid_vnr(current)) + return -EPERM; + + if (copy_from_user(&kdata, data, + tocopy * sizeof(struct __user_cap_data_struct))) return -EFAULT; - } for (i = 0; i < tocopy; i++) { effective.cap[i] = kdata[i].effective; @@ -457,32 +271,21 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) i++; } - if (pid && (pid != task_pid_vnr(current))) - ret = do_sys_capset_other_tasks(pid, &effective, &inheritable, - &permitted); - else { - /* - * This lock is required even when filesystem - * capability support is configured - it protects the - * sys_capget() call from returning incorrect data in - * the case that the targeted process is not the - * current one. - */ - spin_lock(&task_capability_lock); + new = prepare_creds(); + if (!new) + return -ENOMEM; - ret = security_capset_check(current, &effective, &inheritable, - &permitted); - /* - * Having verified that the proposed changes are - * legal, we now put them into effect. - */ - if (!ret) - security_capset_set(current, &effective, &inheritable, - &permitted); - spin_unlock(&task_capability_lock); - } + ret = security_capset(new, current_cred(), + &effective, &inheritable, &permitted); + if (ret < 0) + goto error; + + audit_log_capset(pid, new, current_cred()); + return commit_creds(new); +error: + abort_creds(new); return ret; } @@ -498,7 +301,12 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) */ int capable(int cap) { - if (has_capability(current, cap)) { + if (unlikely(!cap_valid(cap))) { + printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap); + BUG(); + } + + if (security_capable(cap) == 0) { current->flags |= PF_SUPERPRIV; return 1; } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2606d0f..c298310 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -84,7 +84,7 @@ struct cgroupfs_root { /* Tracks how many cgroups are currently defined in hierarchy.*/ int number_of_cgroups; - /* A list running through the mounted hierarchies */ + /* A list running through the active hierarchies */ struct list_head root_list; /* Hierarchy-specific flags */ @@ -116,7 +116,6 @@ static int root_count; * be called. */ static int need_forkexit_callback __read_mostly; -static int need_mm_owner_callback __read_mostly; /* convenient tests for these bits */ inline int cgroup_is_removed(const struct cgroup *cgrp) @@ -149,8 +148,8 @@ static int notify_on_release(const struct cgroup *cgrp) #define for_each_subsys(_root, _ss) \ list_for_each_entry(_ss, &_root->subsys_list, sibling) -/* for_each_root() allows you to iterate across the active hierarchies */ -#define for_each_root(_root) \ +/* for_each_active_root() allows you to iterate across the active hierarchies */ +#define for_each_active_root(_root) \ list_for_each_entry(_root, &roots, root_list) /* the list of cgroups eligible for automatic release. Protected by @@ -272,7 +271,7 @@ static void __put_css_set(struct css_set *cg, int taskexit) rcu_read_lock(); for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - struct cgroup *cgrp = cg->subsys[i]->cgroup; + struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup); if (atomic_dec_and_test(&cgrp->count) && notify_on_release(cgrp)) { if (taskexit) @@ -385,6 +384,25 @@ static int allocate_cg_links(int count, struct list_head *tmp) return 0; } +/** + * link_css_set - a helper function to link a css_set to a cgroup + * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links() + * @cg: the css_set to be linked + * @cgrp: the destination cgroup + */ +static void link_css_set(struct list_head *tmp_cg_links, + struct css_set *cg, struct cgroup *cgrp) +{ + struct cg_cgroup_link *link; + + BUG_ON(list_empty(tmp_cg_links)); + link = list_first_entry(tmp_cg_links, struct cg_cgroup_link, + cgrp_link_list); + link->cg = cg; + list_move(&link->cgrp_link_list, &cgrp->css_sets); + list_add(&link->cg_link_list, &cg->cg_links); +} + /* * find_css_set() takes an existing cgroup group and a * cgroup object, and returns a css_set object that's @@ -400,7 +418,6 @@ static struct css_set *find_css_set( int i; struct list_head tmp_cg_links; - struct cg_cgroup_link *link; struct hlist_head *hhead; @@ -445,26 +462,11 @@ static struct css_set *find_css_set( * only do it for the first subsystem in each * hierarchy */ - if (ss->root->subsys_list.next == &ss->sibling) { - BUG_ON(list_empty(&tmp_cg_links)); - link = list_entry(tmp_cg_links.next, - struct cg_cgroup_link, - cgrp_link_list); - list_del(&link->cgrp_link_list); - list_add(&link->cgrp_link_list, &cgrp->css_sets); - link->cg = res; - list_add(&link->cg_link_list, &res->cg_links); - } - } - if (list_empty(&rootnode.subsys_list)) { - link = list_entry(tmp_cg_links.next, - struct cg_cgroup_link, - cgrp_link_list); - list_del(&link->cgrp_link_list); - list_add(&link->cgrp_link_list, &dummytop->css_sets); - link->cg = res; - list_add(&link->cg_link_list, &res->cg_links); + if (ss->root->subsys_list.next == &ss->sibling) + link_css_set(&tmp_cg_links, res, cgrp); } + if (list_empty(&rootnode.subsys_list)) + link_css_set(&tmp_cg_links, res, dummytop); BUG_ON(!list_empty(&tmp_cg_links)); @@ -571,9 +573,8 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; - inode->i_blocks = 0; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info; } @@ -588,11 +589,18 @@ static void cgroup_call_pre_destroy(struct cgroup *cgrp) { struct cgroup_subsys *ss; for_each_subsys(cgrp->root, ss) - if (ss->pre_destroy && cgrp->subsys[ss->subsys_id]) + if (ss->pre_destroy) ss->pre_destroy(ss, cgrp); return; } +static void free_cgroup_rcu(struct rcu_head *obj) +{ + struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head); + + kfree(cgrp); +} + static void cgroup_diput(struct dentry *dentry, struct inode *inode) { /* is dentry a directory ? if so, kfree() associated cgroup */ @@ -612,19 +620,19 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) /* * Release the subsystem state objects. */ - for_each_subsys(cgrp->root, ss) { - if (cgrp->subsys[ss->subsys_id]) - ss->destroy(ss, cgrp); - } + for_each_subsys(cgrp->root, ss) + ss->destroy(ss, cgrp); cgrp->root->number_of_cgroups--; mutex_unlock(&cgroup_mutex); - /* Drop the active superblock reference that we took when we - * created the cgroup */ + /* + * Drop the active superblock reference that we took when we + * created the cgroup + */ deactivate_super(cgrp->root->sb); - kfree(cgrp); + call_rcu(&cgrp->rcu_head, free_cgroup_rcu); } iput(inode); } @@ -714,23 +722,26 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(cgrp->subsys[i]); BUG_ON(!dummytop->subsys[i]); BUG_ON(dummytop->subsys[i]->cgroup != dummytop); + mutex_lock(&ss->hierarchy_mutex); cgrp->subsys[i] = dummytop->subsys[i]; cgrp->subsys[i]->cgroup = cgrp; - list_add(&ss->sibling, &root->subsys_list); - rcu_assign_pointer(ss->root, root); + list_move(&ss->sibling, &root->subsys_list); + ss->root = root; if (ss->bind) ss->bind(ss, cgrp); - + mutex_unlock(&ss->hierarchy_mutex); } else if (bit & removed_bits) { /* We're removing this subsystem */ BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]); BUG_ON(cgrp->subsys[i]->cgroup != cgrp); + mutex_lock(&ss->hierarchy_mutex); if (ss->bind) ss->bind(ss, dummytop); dummytop->subsys[i]->cgroup = dummytop; cgrp->subsys[i] = NULL; - rcu_assign_pointer(subsys[i]->root, &rootnode); - list_del(&ss->sibling); + subsys[i]->root = &rootnode; + list_move(&ss->sibling, &rootnode.subsys_list); + mutex_unlock(&ss->hierarchy_mutex); } else if (bit & final_bits) { /* Subsystem state should already exist */ BUG_ON(!cgrp->subsys[i]); @@ -992,7 +1003,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, root = NULL; } else { /* New superblock */ - struct cgroup *cgrp = &root->top_cgroup; + struct cgroup *root_cgrp = &root->top_cgroup; struct inode *inode; int i; @@ -1033,7 +1044,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, list_add(&root->root_list, &roots); root_count++; - sb->s_root->d_fsdata = &root->top_cgroup; + sb->s_root->d_fsdata = root_cgrp; root->top_cgroup.dentry = sb->s_root; /* Link the top cgroup in this hierarchy into all @@ -1044,29 +1055,18 @@ static int cgroup_get_sb(struct file_system_type *fs_type, struct hlist_node *node; struct css_set *cg; - hlist_for_each_entry(cg, node, hhead, hlist) { - struct cg_cgroup_link *link; - - BUG_ON(list_empty(&tmp_cg_links)); - link = list_entry(tmp_cg_links.next, - struct cg_cgroup_link, - cgrp_link_list); - list_del(&link->cgrp_link_list); - link->cg = cg; - list_add(&link->cgrp_link_list, - &root->top_cgroup.css_sets); - list_add(&link->cg_link_list, &cg->cg_links); - } + hlist_for_each_entry(cg, node, hhead, hlist) + link_css_set(&tmp_cg_links, cg, root_cgrp); } write_unlock(&css_set_lock); free_cg_links(&tmp_cg_links); - BUG_ON(!list_empty(&cgrp->sibling)); - BUG_ON(!list_empty(&cgrp->children)); + BUG_ON(!list_empty(&root_cgrp->sibling)); + BUG_ON(!list_empty(&root_cgrp->children)); BUG_ON(root->number_of_cgroups != 1); - cgroup_populate_dir(cgrp); + cgroup_populate_dir(root_cgrp); mutex_unlock(&inode->i_mutex); mutex_unlock(&cgroup_mutex); } @@ -1115,10 +1115,9 @@ static void cgroup_kill_sb(struct super_block *sb) { } write_unlock(&css_set_lock); - if (!list_empty(&root->root_list)) { - list_del(&root->root_list); - root_count--; - } + list_del(&root->root_list); + root_count--; + mutex_unlock(&cgroup_mutex); kfree(root); @@ -1147,14 +1146,16 @@ static inline struct cftype *__d_cft(struct dentry *dentry) * @buf: the buffer to write the path into * @buflen: the length of the buffer * - * Called with cgroup_mutex held. Writes path of cgroup into buf. - * Returns 0 on success, -errno on error. + * Called with cgroup_mutex held or else with an RCU-protected cgroup + * reference. Writes path of cgroup into buf. Returns 0 on success, + * -errno on error. */ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) { char *start; + struct dentry *dentry = rcu_dereference(cgrp->dentry); - if (cgrp == dummytop) { + if (!dentry || cgrp == dummytop) { /* * Inactive subsystems have no dentry for their root * cgroup @@ -1167,13 +1168,14 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) *--start = '\0'; for (;;) { - int len = cgrp->dentry->d_name.len; + int len = dentry->d_name.len; if ((start -= len) < buf) return -ENAMETOOLONG; memcpy(start, cgrp->dentry->d_name.name, len); cgrp = cgrp->parent; if (!cgrp) break; + dentry = rcu_dereference(cgrp->dentry); if (!cgrp->parent) continue; if (--start < buf) @@ -1218,7 +1220,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) int retval = 0; struct cgroup_subsys *ss; struct cgroup *oldcgrp; - struct css_set *cg = tsk->cgroups; + struct css_set *cg; struct css_set *newcg; struct cgroupfs_root *root = cgrp->root; int subsys_id; @@ -1238,11 +1240,16 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) } } + task_lock(tsk); + cg = tsk->cgroups; + get_css_set(cg); + task_unlock(tsk); /* * Locate or allocate a new css_set for this task, * based on its final set of cgroups */ newcg = find_css_set(cg, cgrp); + put_css_set(cg); if (!newcg) return -ENOMEM; @@ -1280,6 +1287,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) { struct task_struct *tsk; + const struct cred *cred = current_cred(), *tcred; int ret; if (pid) { @@ -1289,14 +1297,16 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) rcu_read_unlock(); return -ESRCH; } - get_task_struct(tsk); - rcu_read_unlock(); - if ((current->euid) && (current->euid != tsk->uid) - && (current->euid != tsk->suid)) { - put_task_struct(tsk); + tcred = __task_cred(tsk); + if (cred->euid && + cred->euid != tcred->uid && + cred->euid != tcred->suid) { + rcu_read_unlock(); return -EACCES; } + get_task_struct(tsk); + rcu_read_unlock(); } else { tsk = current; get_task_struct(tsk); @@ -1444,7 +1454,7 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *buf, struct cftype *cft = __d_cft(file->f_dentry); struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - if (!cft || cgroup_is_removed(cgrp)) + if (cgroup_is_removed(cgrp)) return -ENODEV; if (cft->write) return cft->write(cgrp, cft, file, buf, nbytes, ppos); @@ -1489,7 +1499,7 @@ static ssize_t cgroup_file_read(struct file *file, char __user *buf, struct cftype *cft = __d_cft(file->f_dentry); struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent); - if (!cft || cgroup_is_removed(cgrp)) + if (cgroup_is_removed(cgrp)) return -ENODEV; if (cft->read) @@ -1553,10 +1563,8 @@ static int cgroup_file_open(struct inode *inode, struct file *file) err = generic_file_open(inode, file); if (err) return err; - cft = __d_cft(file->f_dentry); - if (!cft) - return -ENODEV; + if (cft->read_map || cft->read_seq_string) { struct cgroup_seqfile_state *state = kzalloc(sizeof(*state), GFP_USER); @@ -1670,7 +1678,7 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry, if (!error) { dentry->d_fsdata = cgrp; inc_nlink(parent->d_inode); - cgrp->dentry = dentry; + rcu_assign_pointer(cgrp->dentry, dentry); dget(dentry); } dput(dentry); @@ -1811,6 +1819,7 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, { struct task_struct *res; struct list_head *l = it->task; + struct cg_cgroup_link *link; /* If the iterator cg is NULL, we have no tasks */ if (!it->cg_link) @@ -1818,7 +1827,8 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp, res = list_entry(l, struct task_struct, cg_list); /* Advance iterator to find next entry */ l = l->next; - if (l == &res->cgroups->tasks) { + link = list_entry(it->cg_link, struct cg_cgroup_link, cgrp_link_list); + if (l == &link->cg->tasks) { /* We reached the end of this task list - move on to * the next cg_cgroup_link */ cgroup_advance_iter(cgrp, it); @@ -2012,14 +2022,16 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan) */ static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp) { - int n = 0; + int n = 0, pid; struct cgroup_iter it; struct task_struct *tsk; cgroup_iter_start(cgrp, &it); while ((tsk = cgroup_iter_next(cgrp, &it))) { if (unlikely(n == npids)) break; - pidarray[n++] = task_pid_vnr(tsk); + pid = task_pid_vnr(tsk); + if (pid > 0) + pidarray[n++] = pid; } cgroup_iter_end(cgrp, &it); return n; @@ -2051,7 +2063,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) ret = 0; cgrp = dentry->d_fsdata; - rcu_read_lock(); cgroup_iter_start(cgrp, &it); while ((tsk = cgroup_iter_next(cgrp, &it))) { @@ -2076,7 +2087,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) } cgroup_iter_end(cgrp, &it); - rcu_read_unlock(); err: return ret; } @@ -2323,7 +2333,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, struct cgroup *cgrp) { css->cgroup = cgrp; - atomic_set(&css->refcnt, 0); + atomic_set(&css->refcnt, 1); css->flags = 0; if (cgrp == dummytop) set_bit(CSS_ROOT, &css->flags); @@ -2331,6 +2341,29 @@ static void init_cgroup_css(struct cgroup_subsys_state *css, cgrp->subsys[ss->subsys_id] = css; } +static void cgroup_lock_hierarchy(struct cgroupfs_root *root) +{ + /* We need to take each hierarchy_mutex in a consistent order */ + int i; + + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss->root == root) + mutex_lock_nested(&ss->hierarchy_mutex, i); + } +} + +static void cgroup_unlock_hierarchy(struct cgroupfs_root *root) +{ + int i; + + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss->root == root) + mutex_unlock(&ss->hierarchy_mutex); + } +} + /* * cgroup_create - create a cgroup * @parent: cgroup that will be parent of the new cgroup @@ -2379,7 +2412,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, init_cgroup_css(css, ss, cgrp); } + cgroup_lock_hierarchy(root); list_add(&cgrp->sibling, &cgrp->parent->children); + cgroup_unlock_hierarchy(root); root->number_of_cgroups++; err = cgroup_create_dir(cgrp, dentry, mode); @@ -2430,7 +2465,7 @@ static int cgroup_has_css_refs(struct cgroup *cgrp) { /* Check the reference count on each subsystem. Since we * already established that there are no tasks in the - * cgroup, if the css refcount is also 0, then there should + * cgroup, if the css refcount is also 1, then there should * be no outstanding references, so the subsystem is safe to * destroy. We scan across all subsystems rather than using * the per-hierarchy linked list of mounted subsystems since @@ -2451,19 +2486,67 @@ static int cgroup_has_css_refs(struct cgroup *cgrp) * matter, since it can only happen if the cgroup * has been deleted and hence no longer needs the * release agent to be called anyway. */ - if (css && atomic_read(&css->refcnt)) + if (css && (atomic_read(&css->refcnt) > 1)) return 1; } return 0; } +/* + * Atomically mark all (or else none) of the cgroup's CSS objects as + * CSS_REMOVED. Return true on success, or false if the cgroup has + * busy subsystems. Call with cgroup_mutex held + */ + +static int cgroup_clear_css_refs(struct cgroup *cgrp) +{ + struct cgroup_subsys *ss; + unsigned long flags; + bool failed = false; + local_irq_save(flags); + for_each_subsys(cgrp->root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + int refcnt; + do { + /* We can only remove a CSS with a refcnt==1 */ + refcnt = atomic_read(&css->refcnt); + if (refcnt > 1) { + failed = true; + goto done; + } + BUG_ON(!refcnt); + /* + * Drop the refcnt to 0 while we check other + * subsystems. This will cause any racing + * css_tryget() to spin until we set the + * CSS_REMOVED bits or abort + */ + } while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt); + } + done: + for_each_subsys(cgrp->root, ss) { + struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; + if (failed) { + /* + * Restore old refcnt if we previously managed + * to clear it from 1 to 0 + */ + if (!atomic_read(&css->refcnt)) + atomic_set(&css->refcnt, 1); + } else { + /* Commit the fact that the CSS is removed */ + set_bit(CSS_REMOVED, &css->flags); + } + } + local_irq_restore(flags); + return !failed; +} + static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) { struct cgroup *cgrp = dentry->d_fsdata; struct dentry *d; struct cgroup *parent; - struct super_block *sb; - struct cgroupfs_root *root; /* the vfs holds both inode->i_mutex already */ @@ -2486,12 +2569,10 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) mutex_lock(&cgroup_mutex); parent = cgrp->parent; - root = cgrp->root; - sb = root->sb; if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children) - || cgroup_has_css_refs(cgrp)) { + || !cgroup_clear_css_refs(cgrp)) { mutex_unlock(&cgroup_mutex); return -EBUSY; } @@ -2501,8 +2582,12 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry) if (!list_empty(&cgrp->release_list)) list_del(&cgrp->release_list); spin_unlock(&release_list_lock); - /* delete my sibling from parent->children */ + + cgroup_lock_hierarchy(cgrp->root); + /* delete this cgroup from parent->children */ list_del(&cgrp->sibling); + cgroup_unlock_hierarchy(cgrp->root); + spin_lock(&cgrp->dentry->d_lock); d = dget(cgrp->dentry); spin_unlock(&d->d_lock); @@ -2524,6 +2609,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name); /* Create the top cgroup state for this subsystem */ + list_add(&ss->sibling, &rootnode.subsys_list); ss->root = &rootnode; css = ss->create(ss, dummytop); /* We don't handle early failures gracefully */ @@ -2537,13 +2623,13 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss) init_css_set.subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id]; need_forkexit_callback |= ss->fork || ss->exit; - need_mm_owner_callback |= !!ss->mm_owner_changed; /* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); + mutex_init(&ss->hierarchy_mutex); ss->active = 1; } @@ -2562,7 +2648,6 @@ int __init cgroup_init_early(void) INIT_HLIST_NODE(&init_css_set.hlist); css_set_count = 1; init_cgroup_root(&rootnode); - list_add(&rootnode.root_list, &roots); root_count = 1; init_task.cgroups = &init_css_set; @@ -2669,15 +2754,12 @@ static int proc_cgroup_show(struct seq_file *m, void *v) mutex_lock(&cgroup_mutex); - for_each_root(root) { + for_each_active_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int subsys_id; int count = 0; - /* Skip this hierarchy if it has no active subsystems */ - if (!root->actual_subsys_bits) - continue; seq_printf(m, "%lu:", root->subsys_bits); for_each_subsys(root, ss) seq_printf(m, "%s%s", count++ ? "," : "", ss->name); @@ -2787,37 +2869,6 @@ void cgroup_fork_callbacks(struct task_struct *child) } } -#ifdef CONFIG_MM_OWNER -/** - * cgroup_mm_owner_callbacks - run callbacks when the mm->owner changes - * @p: the new owner - * - * Called on every change to mm->owner. mm_init_owner() does not - * invoke this routine, since it assigns the mm->owner the first time - * and does not change it. - * - * The callbacks are invoked with mmap_sem held in read mode. - */ -void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new) -{ - struct cgroup *oldcgrp, *newcgrp = NULL; - - if (need_mm_owner_callback) { - int i; - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - struct cgroup_subsys *ss = subsys[i]; - oldcgrp = task_cgroup(old, ss->subsys_id); - if (new) - newcgrp = task_cgroup(new, ss->subsys_id); - if (oldcgrp == newcgrp) - continue; - if (ss->mm_owner_changed) - ss->mm_owner_changed(ss, oldcgrp, newcgrp, new); - } - } -} -#endif /* CONFIG_MM_OWNER */ - /** * cgroup_post_fork - called on a new task after adding it to the task list * @child: the task in question @@ -2831,8 +2882,10 @@ void cgroup_post_fork(struct task_struct *child) { if (use_task_css_set_links) { write_lock(&css_set_lock); + task_lock(child); if (list_empty(&child->cg_list)) list_add(&child->cg_list, &child->cgroups->tasks); + task_unlock(child); write_unlock(&css_set_lock); } } @@ -2938,14 +2991,20 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, mutex_unlock(&cgroup_mutex); return 0; } + task_lock(tsk); cg = tsk->cgroups; parent = task_cgroup(tsk, subsys->subsys_id); /* Pin the hierarchy */ - atomic_inc(&parent->root->sb->s_active); + if (!atomic_inc_not_zero(&parent->root->sb->s_active)) { + /* We race with the final deactivate_super() */ + mutex_unlock(&cgroup_mutex); + return 0; + } /* Keep the cgroup alive */ get_css_set(cg); + task_unlock(tsk); mutex_unlock(&cgroup_mutex); /* Now do the VFS work to create a cgroup */ @@ -2964,7 +3023,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, } /* Create the cgroup directory, which also creates the cgroup */ - ret = vfs_mkdir(inode, dentry, S_IFDIR | 0755); + ret = vfs_mkdir(inode, dentry, 0755); child = __d_cgrp(dentry); dput(dentry); if (ret) { @@ -2974,13 +3033,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, goto out_release; } - if (!child) { - printk(KERN_INFO - "Couldn't find new cgroup %s\n", nodename); - ret = -ENOMEM; - goto out_release; - } - /* The cgroup now exists. Retake cgroup_mutex and check * that we're still in the same state that we thought we * were. */ @@ -3076,7 +3128,8 @@ void __css_put(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; rcu_read_lock(); - if (atomic_dec_and_test(&css->refcnt) && notify_on_release(cgrp)) { + if ((atomic_dec_return(&css->refcnt) == 1) && + notify_on_release(cgrp)) { set_bit(CGRP_RELEASABLE, &cgrp->flags); check_for_release(cgrp); } diff --git a/kernel/compat.c b/kernel/compat.c index 8eafe3e..42d5654 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -24,6 +24,7 @@ #include <linux/migrate.h> #include <linux/posix-timers.h> #include <linux/times.h> +#include <linux/ptrace.h> #include <asm/uaccess.h> @@ -229,6 +230,7 @@ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } + force_successful_syscall_return(); return compat_jiffies_to_clock_t(jiffies); } @@ -454,16 +456,16 @@ asmlinkage long compat_sys_waitid(int which, compat_pid_t pid, } static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr, - unsigned len, cpumask_t *new_mask) + unsigned len, struct cpumask *new_mask) { unsigned long *k; - if (len < sizeof(cpumask_t)) - memset(new_mask, 0, sizeof(cpumask_t)); - else if (len > sizeof(cpumask_t)) - len = sizeof(cpumask_t); + if (len < cpumask_size()) + memset(new_mask, 0, cpumask_size()); + else if (len > cpumask_size()) + len = cpumask_size(); - k = cpus_addr(*new_mask); + k = cpumask_bits(new_mask); return compat_get_bitmap(k, user_mask_ptr, len * 8); } @@ -471,40 +473,51 @@ asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr) { - cpumask_t new_mask; + cpumask_var_t new_mask; int retval; - retval = compat_get_user_cpu_mask(user_mask_ptr, len, &new_mask); + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = compat_get_user_cpu_mask(user_mask_ptr, len, new_mask); if (retval) - return retval; + goto out; - return sched_setaffinity(pid, &new_mask); + retval = sched_setaffinity(pid, new_mask); +out: + free_cpumask_var(new_mask); + return retval; } asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr) { int ret; - cpumask_t mask; + cpumask_var_t mask; unsigned long *k; - unsigned int min_length = sizeof(cpumask_t); + unsigned int min_length = cpumask_size(); - if (NR_CPUS <= BITS_PER_COMPAT_LONG) + if (nr_cpu_ids <= BITS_PER_COMPAT_LONG) min_length = sizeof(compat_ulong_t); if (len < min_length) return -EINVAL; - ret = sched_getaffinity(pid, &mask); + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); if (ret < 0) - return ret; + goto out; - k = cpus_addr(mask); + k = cpumask_bits(mask); ret = compat_put_bitmap(user_mask_ptr, k, min_length * 8); - if (ret) - return ret; + if (ret == 0) + ret = min_length; - return min_length; +out: + free_cpumask_var(mask); + return ret; } int get_compat_itimerspec(struct itimerspec *dst, @@ -883,8 +896,9 @@ asmlinkage long compat_sys_time(compat_time_t __user * tloc) if (tloc) { if (put_user(i,tloc)) - i = -EFAULT; + return -EFAULT; } + force_successful_syscall_return(); return i; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 8ea32e8..79e40f0 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -15,29 +15,8 @@ #include <linux/stop_machine.h> #include <linux/mutex.h> -/* - * Represents all cpu's present in the system - * In systems capable of hotplug, this map could dynamically grow - * as new cpu's are detected in the system via any platform specific - * method, such as ACPI for e.g. - */ -cpumask_t cpu_present_map __read_mostly; -EXPORT_SYMBOL(cpu_present_map); - -#ifndef CONFIG_SMP - -/* - * Represents all cpu's that are currently online. - */ -cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL; -EXPORT_SYMBOL(cpu_online_map); - -cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL; -EXPORT_SYMBOL(cpu_possible_map); - -#else /* CONFIG_SMP */ - -/* Serializes the updates to cpu_online_map, cpu_present_map */ +#ifdef CONFIG_SMP +/* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain); @@ -64,8 +43,6 @@ void __init cpu_hotplug_init(void) cpu_hotplug.refcount = 0; } -cpumask_t cpu_active_map; - #ifdef CONFIG_HOTPLUG_CPU void get_online_cpus(void) @@ -96,7 +73,7 @@ EXPORT_SYMBOL_GPL(put_online_cpus); /* * The following two API's must be used when attempting - * to serialize the updates to cpu_online_map, cpu_present_map. + * to serialize the updates to cpu_online_mask, cpu_present_mask. */ void cpu_maps_update_begin(void) { @@ -217,7 +194,7 @@ static int __ref take_cpu_down(void *_param) static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) { int err, nr_calls = 0; - cpumask_t old_allowed, tmp; + cpumask_var_t old_allowed; void *hcpu = (void *)(long)cpu; unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; struct take_cpu_down_param tcd_param = { @@ -231,6 +208,9 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) if (!cpu_online(cpu)) return -EINVAL; + if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL)) + return -ENOMEM; + cpu_hotplug_begin(); err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); @@ -245,13 +225,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) } /* Ensure that we are not runnable on dying cpu */ - old_allowed = current->cpus_allowed; - cpus_setall(tmp); - cpu_clear(cpu, tmp); - set_cpus_allowed_ptr(current, &tmp); - tmp = cpumask_of_cpu(cpu); + cpumask_copy(old_allowed, ¤t->cpus_allowed); + set_cpus_allowed_ptr(current, + cpumask_of(cpumask_any_but(cpu_online_mask, cpu))); - err = __stop_machine(take_cpu_down, &tcd_param, &tmp); + err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod, @@ -277,7 +255,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) check_for_tasks(cpu); out_allowed: - set_cpus_allowed_ptr(current, &old_allowed); + set_cpus_allowed_ptr(current, old_allowed); out_release: cpu_hotplug_done(); if (!err) { @@ -285,13 +263,17 @@ out_release: hcpu) == NOTIFY_BAD) BUG(); } + free_cpumask_var(old_allowed); return err; } int __ref cpu_down(unsigned int cpu) { - int err = 0; + int err; + err = stop_machine_create(); + if (err) + return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { @@ -303,7 +285,7 @@ int __ref cpu_down(unsigned int cpu) /* * Make sure the all cpus did the reschedule and are not - * using stale version of the cpu_active_map. + * using stale version of the cpu_active_mask. * This is not strictly necessary becuase stop_machine() * that we run down the line already provides the required * synchronization. But it's really a side effect and we do not @@ -318,6 +300,7 @@ int __ref cpu_down(unsigned int cpu) out: cpu_maps_update_done(); + stop_machine_destroy(); return err; } EXPORT_SYMBOL(cpu_down); @@ -367,7 +350,7 @@ out_notify: int __cpuinit cpu_up(unsigned int cpu) { int err = 0; - if (!cpu_isset(cpu, cpu_possible_map)) { + if (!cpu_possible(cpu)) { printk(KERN_ERR "can't online cpu %d because it is not " "configured as may-hotadd at boot time\n", cpu); #if defined(CONFIG_IA64) || defined(CONFIG_X86_64) @@ -392,25 +375,28 @@ out: } #ifdef CONFIG_PM_SLEEP_SMP -static cpumask_t frozen_cpus; +static cpumask_var_t frozen_cpus; int disable_nonboot_cpus(void) { - int cpu, first_cpu, error = 0; + int cpu, first_cpu, error; + error = stop_machine_create(); + if (error) + return error; cpu_maps_update_begin(); - first_cpu = first_cpu(cpu_online_map); + first_cpu = cpumask_first(cpu_online_mask); /* We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ - cpus_clear(frozen_cpus); + cpumask_clear(frozen_cpus); printk("Disabling non-boot CPUs ...\n"); for_each_online_cpu(cpu) { if (cpu == first_cpu) continue; error = _cpu_down(cpu, 1); if (!error) { - cpu_set(cpu, frozen_cpus); + cpumask_set_cpu(cpu, frozen_cpus); printk("CPU%d is down\n", cpu); } else { printk(KERN_ERR "Error taking CPU%d down: %d\n", @@ -426,6 +412,7 @@ int disable_nonboot_cpus(void) printk(KERN_ERR "Non-boot CPUs are not disabled\n"); } cpu_maps_update_done(); + stop_machine_destroy(); return error; } @@ -436,11 +423,11 @@ void __ref enable_nonboot_cpus(void) /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); cpu_hotplug_disabled = 0; - if (cpus_empty(frozen_cpus)) + if (cpumask_empty(frozen_cpus)) goto out; printk("Enabling non-boot CPUs ...\n"); - for_each_cpu_mask_nr(cpu, frozen_cpus) { + for_each_cpu(cpu, frozen_cpus) { error = _cpu_up(cpu, 1); if (!error) { printk("CPU%d is up\n", cpu); @@ -448,10 +435,18 @@ void __ref enable_nonboot_cpus(void) } printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error); } - cpus_clear(frozen_cpus); + cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } + +static int alloc_frozen_cpus(void) +{ + if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) + return -ENOMEM; + return 0; +} +core_initcall(alloc_frozen_cpus); #endif /* CONFIG_PM_SLEEP_SMP */ /** @@ -467,7 +462,7 @@ void __cpuinit notify_cpu_starting(unsigned int cpu) unsigned long val = CPU_STARTING; #ifdef CONFIG_PM_SLEEP_SMP - if (cpu_isset(cpu, frozen_cpus)) + if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus)) val = CPU_STARTING_FROZEN; #endif /* CONFIG_PM_SLEEP_SMP */ raw_notifier_call_chain(&cpu_chain, val, (void *)(long)cpu); @@ -479,7 +474,7 @@ void __cpuinit notify_cpu_starting(unsigned int cpu) * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * - * It is used by cpumask_of_cpu() to get a constant address to a CPU + * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ @@ -502,3 +497,71 @@ EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); + +#ifdef CONFIG_INIT_ALL_POSSIBLE +static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly + = CPU_BITS_ALL; +#else +static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly; +#endif +const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits); +EXPORT_SYMBOL(cpu_possible_mask); + +static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly; +const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits); +EXPORT_SYMBOL(cpu_online_mask); + +static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly; +const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits); +EXPORT_SYMBOL(cpu_present_mask); + +static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly; +const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits); +EXPORT_SYMBOL(cpu_active_mask); + +void set_cpu_possible(unsigned int cpu, bool possible) +{ + if (possible) + cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits)); + else + cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits)); +} + +void set_cpu_present(unsigned int cpu, bool present) +{ + if (present) + cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits)); + else + cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits)); +} + +void set_cpu_online(unsigned int cpu, bool online) +{ + if (online) + cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits)); + else + cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits)); +} + +void set_cpu_active(unsigned int cpu, bool active) +{ + if (active) + cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits)); + else + cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits)); +} + +void init_cpu_present(const struct cpumask *src) +{ + cpumask_copy(to_cpumask(cpu_present_bits), src); +} + +void init_cpu_possible(const struct cpumask *src) +{ + cpumask_copy(to_cpumask(cpu_possible_bits), src); +} + +void init_cpu_online(const struct cpumask *src) +{ + cpumask_copy(to_cpumask(cpu_online_bits), src); +} diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 96c0ba1..647c77a 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -84,7 +84,7 @@ struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ - cpumask_t cpus_allowed; /* CPUs allowed to tasks in cpuset */ + cpumask_var_t cpus_allowed; /* CPUs allowed to tasks in cpuset */ nodemask_t mems_allowed; /* Memory Nodes allowed to tasks */ struct cpuset *parent; /* my parent */ @@ -195,8 +195,6 @@ static int cpuset_mems_generation; static struct cpuset top_cpuset = { .flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), - .cpus_allowed = CPU_MASK_ALL, - .mems_allowed = NODE_MASK_ALL, }; /* @@ -240,6 +238,17 @@ static struct cpuset top_cpuset = { static DEFINE_MUTEX(callback_mutex); /* + * cpuset_buffer_lock protects both the cpuset_name and cpuset_nodelist + * buffers. They are statically allocated to prevent using excess stack + * when calling cpuset_print_task_mems_allowed(). + */ +#define CPUSET_NAME_LEN (128) +#define CPUSET_NODELIST_LEN (256) +static char cpuset_name[CPUSET_NAME_LEN]; +static char cpuset_nodelist[CPUSET_NODELIST_LEN]; +static DEFINE_SPINLOCK(cpuset_buffer_lock); + +/* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead @@ -267,7 +276,7 @@ static struct file_system_type cpuset_fs_type = { }; /* - * Return in *pmask the portion of a cpusets's cpus_allowed that + * Return in pmask the portion of a cpusets's cpus_allowed that * are online. If none are online, walk up the cpuset hierarchy * until we find one that does have some online cpus. If we get * all the way to the top and still haven't found any online cpus, @@ -280,15 +289,16 @@ static struct file_system_type cpuset_fs_type = { * Call with callback_mutex held. */ -static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask) +static void guarantee_online_cpus(const struct cpuset *cs, + struct cpumask *pmask) { - while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map)) + while (cs && !cpumask_intersects(cs->cpus_allowed, cpu_online_mask)) cs = cs->parent; if (cs) - cpus_and(*pmask, cs->cpus_allowed, cpu_online_map); + cpumask_and(pmask, cs->cpus_allowed, cpu_online_mask); else - *pmask = cpu_online_map; - BUG_ON(!cpus_intersects(*pmask, cpu_online_map)); + cpumask_copy(pmask, cpu_online_mask); + BUG_ON(!cpumask_intersects(pmask, cpu_online_mask)); } /* @@ -364,14 +374,9 @@ void cpuset_update_task_memory_state(void) struct task_struct *tsk = current; struct cpuset *cs; - if (task_cs(tsk) == &top_cpuset) { - /* Don't need rcu for top_cpuset. It's never freed. */ - my_cpusets_mem_gen = top_cpuset.mems_generation; - } else { - rcu_read_lock(); - my_cpusets_mem_gen = task_cs(tsk)->mems_generation; - rcu_read_unlock(); - } + rcu_read_lock(); + my_cpusets_mem_gen = task_cs(tsk)->mems_generation; + rcu_read_unlock(); if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) { mutex_lock(&callback_mutex); @@ -403,12 +408,43 @@ void cpuset_update_task_memory_state(void) static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { - return cpus_subset(p->cpus_allowed, q->cpus_allowed) && + return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); } +/** + * alloc_trial_cpuset - allocate a trial cpuset + * @cs: the cpuset that the trial cpuset duplicates + */ +static struct cpuset *alloc_trial_cpuset(const struct cpuset *cs) +{ + struct cpuset *trial; + + trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); + if (!trial) + return NULL; + + if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) { + kfree(trial); + return NULL; + } + cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); + + return trial; +} + +/** + * free_trial_cpuset - free the trial cpuset + * @trial: the trial cpuset to be freed + */ +static void free_trial_cpuset(struct cpuset *trial) +{ + free_cpumask_var(trial->cpus_allowed); + kfree(trial); +} + /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. @@ -458,7 +494,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) c = cgroup_cs(cont); if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && - cpus_intersects(trial->cpus_allowed, c->cpus_allowed)) + cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) return -EINVAL; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && @@ -468,7 +504,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) /* Cpusets with tasks can't have empty cpus_allowed or mems_allowed */ if (cgroup_task_count(cur->css.cgroup)) { - if (cpus_empty(trial->cpus_allowed) || + if (cpumask_empty(trial->cpus_allowed) || nodes_empty(trial->mems_allowed)) { return -ENOSPC; } @@ -483,7 +519,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial) */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { - return cpus_intersects(a->cpus_allowed, b->cpus_allowed); + return cpumask_intersects(a->cpus_allowed, b->cpus_allowed); } static void @@ -508,7 +544,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) cp = list_first_entry(&q, struct cpuset, stack_list); list_del(q.next); - if (cpus_empty(cp->cpus_allowed)) + if (cpumask_empty(cp->cpus_allowed)) continue; if (is_sched_load_balance(cp)) @@ -575,7 +611,8 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c) * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ -static int generate_sched_domains(cpumask_t **domains, +/* FIXME: see the FIXME in partition_sched_domains() */ +static int generate_sched_domains(struct cpumask **domains, struct sched_domain_attr **attributes) { LIST_HEAD(q); /* queue of cpusets to be scanned */ @@ -583,10 +620,10 @@ static int generate_sched_domains(cpumask_t **domains, struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ - cpumask_t *doms; /* resulting partition; i.e. sched domains */ + struct cpumask *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ - int nslot; /* next empty doms[] cpumask_t slot */ + int nslot; /* next empty doms[] struct cpumask slot */ doms = NULL; dattr = NULL; @@ -594,7 +631,7 @@ static int generate_sched_domains(cpumask_t **domains, /* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance(&top_cpuset)) { - doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL); + doms = kmalloc(cpumask_size(), GFP_KERNEL); if (!doms) goto done; @@ -603,7 +640,7 @@ static int generate_sched_domains(cpumask_t **domains, *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } - *doms = top_cpuset.cpus_allowed; + cpumask_copy(doms, top_cpuset.cpus_allowed); ndoms = 1; goto done; @@ -622,7 +659,7 @@ static int generate_sched_domains(cpumask_t **domains, cp = list_first_entry(&q, struct cpuset, stack_list); list_del(q.next); - if (cpus_empty(cp->cpus_allowed)) + if (cpumask_empty(cp->cpus_allowed)) continue; /* @@ -673,7 +710,7 @@ restart: * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ - doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL); + doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL); if (!doms) goto done; @@ -685,7 +722,7 @@ restart: for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; - cpumask_t *dp; + struct cpumask *dp; int apn = a->pn; if (apn < 0) { @@ -708,14 +745,14 @@ restart: continue; } - cpus_clear(*dp); + cpumask_clear(dp); if (dattr) *(dattr + nslot) = SD_ATTR_INIT; for (j = i; j < csn; j++) { struct cpuset *b = csa[j]; if (apn == b->pn) { - cpus_or(*dp, *dp, b->cpus_allowed); + cpumask_or(dp, dp, b->cpus_allowed); if (dattr) update_domain_attr_tree(dattr + nslot, b); @@ -755,7 +792,7 @@ done: static void do_rebuild_sched_domains(struct work_struct *unused) { struct sched_domain_attr *attr; - cpumask_t *doms; + struct cpumask *doms; int ndoms; get_online_cpus(); @@ -824,7 +861,7 @@ void rebuild_sched_domains(void) static int cpuset_test_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan) { - return !cpus_equal(tsk->cpus_allowed, + return !cpumask_equal(&tsk->cpus_allowed, (cgroup_cs(scan->cg))->cpus_allowed); } @@ -842,7 +879,7 @@ static int cpuset_test_cpumask(struct task_struct *tsk, static void cpuset_change_cpumask(struct task_struct *tsk, struct cgroup_scanner *scan) { - set_cpus_allowed_ptr(tsk, &((cgroup_cs(scan->cg))->cpus_allowed)); + set_cpus_allowed_ptr(tsk, ((cgroup_cs(scan->cg))->cpus_allowed)); } /** @@ -874,10 +911,10 @@ static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap) * @cs: the cpuset to consider * @buf: buffer of cpu numbers written to this cpuset */ -static int update_cpumask(struct cpuset *cs, const char *buf) +static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, + const char *buf) { struct ptr_heap heap; - struct cpuset trialcs; int retval; int is_load_balanced; @@ -885,8 +922,6 @@ static int update_cpumask(struct cpuset *cs, const char *buf) if (cs == &top_cpuset) return -EACCES; - trialcs = *cs; - /* * An empty cpus_allowed is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case @@ -894,31 +929,31 @@ static int update_cpumask(struct cpuset *cs, const char *buf) * with tasks have cpus. */ if (!*buf) { - cpus_clear(trialcs.cpus_allowed); + cpumask_clear(trialcs->cpus_allowed); } else { - retval = cpulist_parse(buf, trialcs.cpus_allowed); + retval = cpulist_parse(buf, trialcs->cpus_allowed); if (retval < 0) return retval; - if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map)) + if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask)) return -EINVAL; } - retval = validate_change(cs, &trialcs); + retval = validate_change(cs, trialcs); if (retval < 0) return retval; /* Nothing to do if the cpus didn't change */ - if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed)) + if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) return 0; retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); if (retval) return retval; - is_load_balanced = is_sched_load_balance(&trialcs); + is_load_balanced = is_sched_load_balance(trialcs); mutex_lock(&callback_mutex); - cs->cpus_allowed = trialcs.cpus_allowed; + cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); mutex_unlock(&callback_mutex); /* @@ -1006,7 +1041,7 @@ static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem) cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ fudge = 10; /* spare mmarray[] slots */ - fudge += cpus_weight(cs->cpus_allowed); /* imagine one fork-bomb/cpu */ + fudge += cpumask_weight(cs->cpus_allowed);/* imagine 1 fork-bomb/cpu */ retval = -ENOMEM; /* @@ -1093,9 +1128,9 @@ done: * lock each such tasks mm->mmap_sem, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ -static int update_nodemask(struct cpuset *cs, const char *buf) +static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, + const char *buf) { - struct cpuset trialcs; nodemask_t oldmem; int retval; @@ -1106,8 +1141,6 @@ static int update_nodemask(struct cpuset *cs, const char *buf) if (cs == &top_cpuset) return -EACCES; - trialcs = *cs; - /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * Since nodelist_parse() fails on an empty mask, we special case @@ -1115,27 +1148,27 @@ static int update_nodemask(struct cpuset *cs, const char *buf) * with tasks have memory. */ if (!*buf) { - nodes_clear(trialcs.mems_allowed); + nodes_clear(trialcs->mems_allowed); } else { - retval = nodelist_parse(buf, trialcs.mems_allowed); + retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) goto done; - if (!nodes_subset(trialcs.mems_allowed, + if (!nodes_subset(trialcs->mems_allowed, node_states[N_HIGH_MEMORY])) return -EINVAL; } oldmem = cs->mems_allowed; - if (nodes_equal(oldmem, trialcs.mems_allowed)) { + if (nodes_equal(oldmem, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } - retval = validate_change(cs, &trialcs); + retval = validate_change(cs, trialcs); if (retval < 0) goto done; mutex_lock(&callback_mutex); - cs->mems_allowed = trialcs.mems_allowed; + cs->mems_allowed = trialcs->mems_allowed; cs->mems_generation = cpuset_mems_generation++; mutex_unlock(&callback_mutex); @@ -1156,7 +1189,8 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) if (val != cs->relax_domain_level) { cs->relax_domain_level = val; - if (!cpus_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) + if (!cpumask_empty(cs->cpus_allowed) && + is_sched_load_balance(cs)) async_rebuild_sched_domains(); } @@ -1175,31 +1209,36 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { - struct cpuset trialcs; + struct cpuset *trialcs; int err; int balance_flag_changed; - trialcs = *cs; + trialcs = alloc_trial_cpuset(cs); + if (!trialcs) + return -ENOMEM; + if (turning_on) - set_bit(bit, &trialcs.flags); + set_bit(bit, &trialcs->flags); else - clear_bit(bit, &trialcs.flags); + clear_bit(bit, &trialcs->flags); - err = validate_change(cs, &trialcs); + err = validate_change(cs, trialcs); if (err < 0) - return err; + goto out; balance_flag_changed = (is_sched_load_balance(cs) != - is_sched_load_balance(&trialcs)); + is_sched_load_balance(trialcs)); mutex_lock(&callback_mutex); - cs->flags = trialcs.flags; + cs->flags = trialcs->flags; mutex_unlock(&callback_mutex); - if (!cpus_empty(trialcs.cpus_allowed) && balance_flag_changed) + if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) async_rebuild_sched_domains(); - return 0; +out: + free_trial_cpuset(trialcs); + return err; } /* @@ -1300,42 +1339,47 @@ static int fmeter_getrate(struct fmeter *fmp) return val; } +/* Protected by cgroup_lock */ +static cpumask_var_t cpus_attach; + /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct task_struct *tsk) { struct cpuset *cs = cgroup_cs(cont); + int ret = 0; - if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) + if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) return -ENOSPC; - if (tsk->flags & PF_THREAD_BOUND) { - cpumask_t mask; + if (tsk->flags & PF_THREAD_BOUND) { mutex_lock(&callback_mutex); - mask = cs->cpus_allowed; + if (!cpumask_equal(&tsk->cpus_allowed, cs->cpus_allowed)) + ret = -EINVAL; mutex_unlock(&callback_mutex); - if (!cpus_equal(tsk->cpus_allowed, mask)) - return -EINVAL; } - return security_task_setscheduler(tsk, 0, NULL); + return ret < 0 ? ret : security_task_setscheduler(tsk, 0, NULL); } static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct cgroup *oldcont, struct task_struct *tsk) { - cpumask_t cpus; nodemask_t from, to; struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); int err; - mutex_lock(&callback_mutex); - guarantee_online_cpus(cs, &cpus); - err = set_cpus_allowed_ptr(tsk, &cpus); - mutex_unlock(&callback_mutex); + if (cs == &top_cpuset) { + cpumask_copy(cpus_attach, cpu_possible_mask); + } else { + mutex_lock(&callback_mutex); + guarantee_online_cpus(cs, cpus_attach); + mutex_unlock(&callback_mutex); + } + err = set_cpus_allowed_ptr(tsk, cpus_attach); if (err) return; @@ -1348,7 +1392,6 @@ static void cpuset_attach(struct cgroup_subsys *ss, cpuset_migrate_mm(mm, &from, &to); mmput(mm); } - } /* The various types of files and directories in a cpuset file system */ @@ -1443,21 +1486,29 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, const char *buf) { int retval = 0; + struct cpuset *cs = cgroup_cs(cgrp); + struct cpuset *trialcs; if (!cgroup_lock_live_group(cgrp)) return -ENODEV; + trialcs = alloc_trial_cpuset(cs); + if (!trialcs) + return -ENOMEM; + switch (cft->private) { case FILE_CPULIST: - retval = update_cpumask(cgroup_cs(cgrp), buf); + retval = update_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: - retval = update_nodemask(cgroup_cs(cgrp), buf); + retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } + + free_trial_cpuset(trialcs); cgroup_unlock(); return retval; } @@ -1476,13 +1527,13 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs) { - cpumask_t mask; + int ret; mutex_lock(&callback_mutex); - mask = cs->cpus_allowed; + ret = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed); mutex_unlock(&callback_mutex); - return cpulist_scnprintf(page, PAGE_SIZE, mask); + return ret; } static int cpuset_sprintf_memlist(char *page, struct cpuset *cs) @@ -1718,7 +1769,7 @@ static void cpuset_post_clone(struct cgroup_subsys *ss, parent_cs = cgroup_cs(parent); cs->mems_allowed = parent_cs->mems_allowed; - cs->cpus_allowed = parent_cs->cpus_allowed; + cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed); return; } @@ -1744,6 +1795,10 @@ static struct cgroup_subsys_state *cpuset_create( cs = kmalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); + if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) { + kfree(cs); + return ERR_PTR(-ENOMEM); + } cpuset_update_task_memory_state(); cs->flags = 0; @@ -1752,7 +1807,7 @@ static struct cgroup_subsys_state *cpuset_create( if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); - cpus_clear(cs->cpus_allowed); + cpumask_clear(cs->cpus_allowed); nodes_clear(cs->mems_allowed); cs->mems_generation = cpuset_mems_generation++; fmeter_init(&cs->fmeter); @@ -1779,6 +1834,7 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); number_of_cpusets--; + free_cpumask_var(cs->cpus_allowed); kfree(cs); } @@ -1802,6 +1858,8 @@ struct cgroup_subsys cpuset_subsys = { int __init cpuset_init_early(void) { + alloc_bootmem_cpumask_var(&top_cpuset.cpus_allowed); + top_cpuset.mems_generation = cpuset_mems_generation++; return 0; } @@ -1817,7 +1875,7 @@ int __init cpuset_init(void) { int err = 0; - cpus_setall(top_cpuset.cpus_allowed); + cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); fmeter_init(&top_cpuset.fmeter); @@ -1829,6 +1887,9 @@ int __init cpuset_init(void) if (err < 0) return err; + if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)) + BUG(); + number_of_cpusets = 1; return 0; } @@ -1903,7 +1964,7 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) * has online cpus, so can't be empty). */ parent = cs->parent; - while (cpus_empty(parent->cpus_allowed) || + while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) parent = parent->parent; @@ -1944,7 +2005,7 @@ static void scan_for_empty_cpusets(struct cpuset *root) } /* Continue past cpusets with all cpus, mems online */ - if (cpus_subset(cp->cpus_allowed, cpu_online_map) && + if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) && nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY])) continue; @@ -1952,13 +2013,14 @@ static void scan_for_empty_cpusets(struct cpuset *root) /* Remove offline cpus and mems from this cpuset. */ mutex_lock(&callback_mutex); - cpus_and(cp->cpus_allowed, cp->cpus_allowed, cpu_online_map); + cpumask_and(cp->cpus_allowed, cp->cpus_allowed, + cpu_online_mask); nodes_and(cp->mems_allowed, cp->mems_allowed, node_states[N_HIGH_MEMORY]); mutex_unlock(&callback_mutex); /* Move tasks from the empty cpuset to a parent */ - if (cpus_empty(cp->cpus_allowed) || + if (cpumask_empty(cp->cpus_allowed) || nodes_empty(cp->mems_allowed)) remove_tasks_in_empty_cpuset(cp); else { @@ -1984,7 +2046,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, unsigned long phase, void *unused_cpu) { struct sched_domain_attr *attr; - cpumask_t *doms; + struct cpumask *doms; int ndoms; switch (phase) { @@ -1999,7 +2061,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, } cgroup_lock(); - top_cpuset.cpus_allowed = cpu_online_map; + cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask); scan_for_empty_cpusets(&top_cpuset); ndoms = generate_sched_domains(&doms, &attr); cgroup_unlock(); @@ -2044,7 +2106,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self, void __init cpuset_init_smp(void) { - top_cpuset.cpus_allowed = cpu_online_map; + cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; hotcpu_notifier(cpuset_track_online_cpus, 0); @@ -2054,15 +2116,15 @@ void __init cpuset_init_smp(void) /** * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. - * @pmask: pointer to cpumask_t variable to receive cpus_allowed set. + * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * - * Description: Returns the cpumask_t cpus_allowed of the cpuset + * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_map, even if this means going outside the * tasks cpuset. **/ -void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask) +void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { mutex_lock(&callback_mutex); cpuset_cpus_allowed_locked(tsk, pmask); @@ -2073,7 +2135,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask) * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset. * Must be called with callback_mutex held. **/ -void cpuset_cpus_allowed_locked(struct task_struct *tsk, cpumask_t *pmask) +void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask) { task_lock(tsk); guarantee_online_cpus(task_cs(tsk), pmask); @@ -2356,6 +2418,29 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } +/** + * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed + * @task: pointer to task_struct of some task. + * + * Description: Prints @task's name, cpuset name, and cached copy of its + * mems_allowed to the kernel log. Must hold task_lock(task) to allow + * dereferencing task_cs(task). + */ +void cpuset_print_task_mems_allowed(struct task_struct *tsk) +{ + struct dentry *dentry; + + dentry = task_cs(tsk)->css.cgroup->dentry; + spin_lock(&cpuset_buffer_lock); + snprintf(cpuset_name, CPUSET_NAME_LEN, + dentry ? (const char *)dentry->d_name.name : "/"); + nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN, + tsk->mems_allowed); + printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n", + tsk->comm, cpuset_name, cpuset_nodelist); + spin_unlock(&cpuset_buffer_lock); +} + /* * Collection of memory_pressure is suppressed unless * this flag is enabled by writing "1" to the special diff --git a/kernel/cred-internals.h b/kernel/cred-internals.h new file mode 100644 index 0000000..2dc4fc2 --- /dev/null +++ b/kernel/cred-internals.h @@ -0,0 +1,21 @@ +/* Internal credentials stuff + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +/* + * user.c + */ +static inline void sched_switch_user(struct task_struct *p) +{ +#ifdef CONFIG_USER_SCHED + sched_move_task(p); +#endif /* CONFIG_USER_SCHED */ +} + diff --git a/kernel/cred.c b/kernel/cred.c new file mode 100644 index 0000000..ff7bc07 --- /dev/null +++ b/kernel/cred.c @@ -0,0 +1,588 @@ +/* Task credentials management - see Documentation/credentials.txt + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ +#include <linux/module.h> +#include <linux/cred.h> +#include <linux/sched.h> +#include <linux/key.h> +#include <linux/keyctl.h> +#include <linux/init_task.h> +#include <linux/security.h> +#include <linux/cn_proc.h> +#include "cred-internals.h" + +static struct kmem_cache *cred_jar; + +/* + * The common credentials for the initial task's thread group + */ +#ifdef CONFIG_KEYS +static struct thread_group_cred init_tgcred = { + .usage = ATOMIC_INIT(2), + .tgid = 0, + .lock = SPIN_LOCK_UNLOCKED, +}; +#endif + +/* + * The initial credentials for the initial task + */ +struct cred init_cred = { + .usage = ATOMIC_INIT(4), + .securebits = SECUREBITS_DEFAULT, + .cap_inheritable = CAP_INIT_INH_SET, + .cap_permitted = CAP_FULL_SET, + .cap_effective = CAP_INIT_EFF_SET, + .cap_bset = CAP_INIT_BSET, + .user = INIT_USER, + .group_info = &init_groups, +#ifdef CONFIG_KEYS + .tgcred = &init_tgcred, +#endif +}; + +/* + * Dispose of the shared task group credentials + */ +#ifdef CONFIG_KEYS +static void release_tgcred_rcu(struct rcu_head *rcu) +{ + struct thread_group_cred *tgcred = + container_of(rcu, struct thread_group_cred, rcu); + + BUG_ON(atomic_read(&tgcred->usage) != 0); + + key_put(tgcred->session_keyring); + key_put(tgcred->process_keyring); + kfree(tgcred); +} +#endif + +/* + * Release a set of thread group credentials. + */ +static void release_tgcred(struct cred *cred) +{ +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred = cred->tgcred; + + if (atomic_dec_and_test(&tgcred->usage)) + call_rcu(&tgcred->rcu, release_tgcred_rcu); +#endif +} + +/* + * The RCU callback to actually dispose of a set of credentials + */ +static void put_cred_rcu(struct rcu_head *rcu) +{ + struct cred *cred = container_of(rcu, struct cred, rcu); + + if (atomic_read(&cred->usage) != 0) + panic("CRED: put_cred_rcu() sees %p with usage %d\n", + cred, atomic_read(&cred->usage)); + + security_cred_free(cred); + key_put(cred->thread_keyring); + key_put(cred->request_key_auth); + release_tgcred(cred); + put_group_info(cred->group_info); + free_uid(cred->user); + kmem_cache_free(cred_jar, cred); +} + +/** + * __put_cred - Destroy a set of credentials + * @cred: The record to release + * + * Destroy a set of credentials on which no references remain. + */ +void __put_cred(struct cred *cred) +{ + BUG_ON(atomic_read(&cred->usage) != 0); + + call_rcu(&cred->rcu, put_cred_rcu); +} +EXPORT_SYMBOL(__put_cred); + +/** + * prepare_creds - Prepare a new set of credentials for modification + * + * Prepare a new set of task credentials for modification. A task's creds + * shouldn't generally be modified directly, therefore this function is used to + * prepare a new copy, which the caller then modifies and then commits by + * calling commit_creds(). + * + * Preparation involves making a copy of the objective creds for modification. + * + * Returns a pointer to the new creds-to-be if successful, NULL otherwise. + * + * Call commit_creds() or abort_creds() to clean up. + */ +struct cred *prepare_creds(void) +{ + struct task_struct *task = current; + const struct cred *old; + struct cred *new; + + BUG_ON(atomic_read(&task->real_cred->usage) < 1); + + new = kmem_cache_alloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + old = task->cred; + memcpy(new, old, sizeof(struct cred)); + + atomic_set(&new->usage, 1); + get_group_info(new->group_info); + get_uid(new->user); + +#ifdef CONFIG_KEYS + key_get(new->thread_keyring); + key_get(new->request_key_auth); + atomic_inc(&new->tgcred->usage); +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + + if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + goto error; + return new; + +error: + abort_creds(new); + return NULL; +} +EXPORT_SYMBOL(prepare_creds); + +/* + * Prepare credentials for current to perform an execve() + * - The caller must hold current->cred_exec_mutex + */ +struct cred *prepare_exec_creds(void) +{ + struct thread_group_cred *tgcred = NULL; + struct cred *new; + +#ifdef CONFIG_KEYS + tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); + if (!tgcred) + return NULL; +#endif + + new = prepare_creds(); + if (!new) { + kfree(tgcred); + return new; + } + +#ifdef CONFIG_KEYS + /* newly exec'd tasks don't get a thread keyring */ + key_put(new->thread_keyring); + new->thread_keyring = NULL; + + /* create a new per-thread-group creds for all this set of threads to + * share */ + memcpy(tgcred, new->tgcred, sizeof(struct thread_group_cred)); + + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + + /* inherit the session keyring; new process keyring */ + key_get(tgcred->session_keyring); + tgcred->process_keyring = NULL; + + release_tgcred(new); + new->tgcred = tgcred; +#endif + + return new; +} + +/* + * prepare new credentials for the usermode helper dispatcher + */ +struct cred *prepare_usermodehelper_creds(void) +{ +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred = NULL; +#endif + struct cred *new; + +#ifdef CONFIG_KEYS + tgcred = kzalloc(sizeof(*new->tgcred), GFP_ATOMIC); + if (!tgcred) + return NULL; +#endif + + new = kmem_cache_alloc(cred_jar, GFP_ATOMIC); + if (!new) + return NULL; + + memcpy(new, &init_cred, sizeof(struct cred)); + + atomic_set(&new->usage, 1); + get_group_info(new->group_info); + get_uid(new->user); + +#ifdef CONFIG_KEYS + new->thread_keyring = NULL; + new->request_key_auth = NULL; + new->jit_keyring = KEY_REQKEY_DEFL_DEFAULT; + + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + new->tgcred = tgcred; +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + if (security_prepare_creds(new, &init_cred, GFP_ATOMIC) < 0) + goto error; + + BUG_ON(atomic_read(&new->usage) != 1); + return new; + +error: + put_cred(new); + return NULL; +} + +/* + * Copy credentials for the new process created by fork() + * + * We share if we can, but under some circumstances we have to generate a new + * set. + * + * The new process gets the current process's subjective credentials as its + * objective and subjective credentials + */ +int copy_creds(struct task_struct *p, unsigned long clone_flags) +{ +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred; +#endif + struct cred *new; + int ret; + + mutex_init(&p->cred_exec_mutex); + + if ( +#ifdef CONFIG_KEYS + !p->cred->thread_keyring && +#endif + clone_flags & CLONE_THREAD + ) { + p->real_cred = get_cred(p->cred); + get_cred(p->cred); + atomic_inc(&p->cred->user->processes); + return 0; + } + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + if (clone_flags & CLONE_NEWUSER) { + ret = create_user_ns(new); + if (ret < 0) + goto error_put; + } + +#ifdef CONFIG_KEYS + /* new threads get their own thread keyrings if their parent already + * had one */ + if (new->thread_keyring) { + key_put(new->thread_keyring); + new->thread_keyring = NULL; + if (clone_flags & CLONE_THREAD) + install_thread_keyring_to_cred(new); + } + + /* we share the process and session keyrings between all the threads in + * a process - this is slightly icky as we violate COW credentials a + * bit */ + if (!(clone_flags & CLONE_THREAD)) { + tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); + if (!tgcred) { + ret = -ENOMEM; + goto error_put; + } + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + tgcred->process_keyring = NULL; + tgcred->session_keyring = key_get(new->tgcred->session_keyring); + + release_tgcred(new); + new->tgcred = tgcred; + } +#endif + + atomic_inc(&new->user->processes); + p->cred = p->real_cred = get_cred(new); + return 0; + +error_put: + put_cred(new); + return ret; +} + +/** + * commit_creds - Install new credentials upon the current task + * @new: The credentials to be assigned + * + * Install a new set of credentials to the current task, using RCU to replace + * the old set. Both the objective and the subjective credentials pointers are + * updated. This function may not be called if the subjective credentials are + * in an overridden state. + * + * This function eats the caller's reference to the new credentials. + * + * Always returns 0 thus allowing this function to be tail-called at the end + * of, say, sys_setgid(). + */ +int commit_creds(struct cred *new) +{ + struct task_struct *task = current; + const struct cred *old; + + BUG_ON(task->cred != task->real_cred); + BUG_ON(atomic_read(&task->real_cred->usage) < 2); + BUG_ON(atomic_read(&new->usage) < 1); + + old = task->real_cred; + security_commit_creds(new, old); + + get_cred(new); /* we will require a ref for the subj creds too */ + + /* dumpability changes */ + if (old->euid != new->euid || + old->egid != new->egid || + old->fsuid != new->fsuid || + old->fsgid != new->fsgid || + !cap_issubset(new->cap_permitted, old->cap_permitted)) { + set_dumpable(task->mm, suid_dumpable); + task->pdeath_signal = 0; + smp_wmb(); + } + + /* alter the thread keyring */ + if (new->fsuid != old->fsuid) + key_fsuid_changed(task); + if (new->fsgid != old->fsgid) + key_fsgid_changed(task); + + /* do it + * - What if a process setreuid()'s and this brings the + * new uid over his NPROC rlimit? We can check this now + * cheaply with the new uid cache, so if it matters + * we should be checking for it. -DaveM + */ + if (new->user != old->user) + atomic_inc(&new->user->processes); + rcu_assign_pointer(task->real_cred, new); + rcu_assign_pointer(task->cred, new); + if (new->user != old->user) + atomic_dec(&old->user->processes); + + sched_switch_user(task); + + /* send notifications */ + if (new->uid != old->uid || + new->euid != old->euid || + new->suid != old->suid || + new->fsuid != old->fsuid) + proc_id_connector(task, PROC_EVENT_UID); + + if (new->gid != old->gid || + new->egid != old->egid || + new->sgid != old->sgid || + new->fsgid != old->fsgid) + proc_id_connector(task, PROC_EVENT_GID); + + /* release the old obj and subj refs both */ + put_cred(old); + put_cred(old); + return 0; +} +EXPORT_SYMBOL(commit_creds); + +/** + * abort_creds - Discard a set of credentials and unlock the current task + * @new: The credentials that were going to be applied + * + * Discard a set of credentials that were under construction and unlock the + * current task. + */ +void abort_creds(struct cred *new) +{ + BUG_ON(atomic_read(&new->usage) < 1); + put_cred(new); +} +EXPORT_SYMBOL(abort_creds); + +/** + * override_creds - Override the current process's subjective credentials + * @new: The credentials to be assigned + * + * Install a set of temporary override subjective credentials on the current + * process, returning the old set for later reversion. + */ +const struct cred *override_creds(const struct cred *new) +{ + const struct cred *old = current->cred; + + rcu_assign_pointer(current->cred, get_cred(new)); + return old; +} +EXPORT_SYMBOL(override_creds); + +/** + * revert_creds - Revert a temporary subjective credentials override + * @old: The credentials to be restored + * + * Revert a temporary set of override subjective credentials to an old set, + * discarding the override set. + */ +void revert_creds(const struct cred *old) +{ + const struct cred *override = current->cred; + + rcu_assign_pointer(current->cred, old); + put_cred(override); +} +EXPORT_SYMBOL(revert_creds); + +/* + * initialise the credentials stuff + */ +void __init cred_init(void) +{ + /* allocate a slab in which we can store credentials */ + cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); +} + +/** + * prepare_kernel_cred - Prepare a set of credentials for a kernel service + * @daemon: A userspace daemon to be used as a reference + * + * Prepare a set of credentials for a kernel service. This can then be used to + * override a task's own credentials so that work can be done on behalf of that + * task that requires a different subjective context. + * + * @daemon is used to provide a base for the security record, but can be NULL. + * If @daemon is supplied, then the security data will be derived from that; + * otherwise they'll be set to 0 and no groups, full capabilities and no keys. + * + * The caller may change these controls afterwards if desired. + * + * Returns the new credentials or NULL if out of memory. + * + * Does not take, and does not return holding current->cred_replace_mutex. + */ +struct cred *prepare_kernel_cred(struct task_struct *daemon) +{ + const struct cred *old; + struct cred *new; + + new = kmem_cache_alloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + if (daemon) + old = get_task_cred(daemon); + else + old = get_cred(&init_cred); + + get_uid(new->user); + get_group_info(new->group_info); + +#ifdef CONFIG_KEYS + atomic_inc(&init_tgcred.usage); + new->tgcred = &init_tgcred; + new->request_key_auth = NULL; + new->thread_keyring = NULL; + new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + goto error; + + atomic_set(&new->usage, 1); + put_cred(old); + return new; + +error: + put_cred(new); + return NULL; +} +EXPORT_SYMBOL(prepare_kernel_cred); + +/** + * set_security_override - Set the security ID in a set of credentials + * @new: The credentials to alter + * @secid: The LSM security ID to set + * + * Set the LSM security ID in a set of credentials so that the subjective + * security is overridden when an alternative set of credentials is used. + */ +int set_security_override(struct cred *new, u32 secid) +{ + return security_kernel_act_as(new, secid); +} +EXPORT_SYMBOL(set_security_override); + +/** + * set_security_override_from_ctx - Set the security ID in a set of credentials + * @new: The credentials to alter + * @secctx: The LSM security context to generate the security ID from. + * + * Set the LSM security ID in a set of credentials so that the subjective + * security is overridden when an alternative set of credentials is used. The + * security ID is specified in string form as a security context to be + * interpreted by the LSM. + */ +int set_security_override_from_ctx(struct cred *new, const char *secctx) +{ + u32 secid; + int ret; + + ret = security_secctx_to_secid(secctx, strlen(secctx), &secid); + if (ret < 0) + return ret; + + return set_security_override(new, secid); +} +EXPORT_SYMBOL(set_security_override_from_ctx); + +/** + * set_create_files_as - Set the LSM file create context in a set of credentials + * @new: The credentials to alter + * @inode: The inode to take the context from + * + * Change the LSM file creation context in a set of credentials to be the same + * as the object context of the specified inode, so that the new inodes have + * the same MAC context as that inode. + */ +int set_create_files_as(struct cred *new, struct inode *inode) +{ + new->fsuid = inode->i_uid; + new->fsgid = inode->i_gid; + return security_kernel_create_files_as(new, inode); +} +EXPORT_SYMBOL(set_create_files_as); diff --git a/kernel/delayacct.c b/kernel/delayacct.c index b3179da..abb6e17 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -127,7 +127,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) */ t1 = tsk->sched_info.pcount; t2 = tsk->sched_info.run_delay; - t3 = tsk->sched_info.cpu_time; + t3 = tsk->se.sum_exec_runtime; d->cpu_count += t1; diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c index f013a0c..0387074 100644 --- a/kernel/dma-coherent.c +++ b/kernel/dma-coherent.c @@ -109,20 +109,40 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied); int dma_alloc_from_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle, void **ret) { - struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + struct dma_coherent_mem *mem; int order = get_order(size); + int pageno; - if (mem) { - int page = bitmap_find_free_region(mem->bitmap, mem->size, - order); - if (page >= 0) { - *dma_handle = mem->device_base + (page << PAGE_SHIFT); - *ret = mem->virt_base + (page << PAGE_SHIFT); - memset(*ret, 0, size); - } else if (mem->flags & DMA_MEMORY_EXCLUSIVE) - *ret = NULL; + if (!dev) + return 0; + mem = dev->dma_mem; + if (!mem) + return 0; + if (unlikely(size > mem->size)) + return 0; + + pageno = bitmap_find_free_region(mem->bitmap, mem->size, order); + if (pageno >= 0) { + /* + * Memory was found in the per-device arena. + */ + *dma_handle = mem->device_base + (pageno << PAGE_SHIFT); + *ret = mem->virt_base + (pageno << PAGE_SHIFT); + memset(*ret, 0, size); + } else if (mem->flags & DMA_MEMORY_EXCLUSIVE) { + /* + * The per-device arena is exhausted and we are not + * permitted to fall back to generic memory. + */ + *ret = NULL; + } else { + /* + * The per-device arena is exhausted and we are + * permitted to fall back to generic memory. + */ + return 0; } - return (mem != NULL); + return 1; } EXPORT_SYMBOL(dma_alloc_from_coherent); diff --git a/kernel/exit.c b/kernel/exit.c index 2d8be7e..c7740fa 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -46,12 +46,18 @@ #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> #include <linux/tracehook.h> +#include <linux/init_task.h> #include <trace/sched.h> #include <asm/uaccess.h> #include <asm/unistd.h> #include <asm/pgtable.h> #include <asm/mmu_context.h> +#include "cred-internals.h" + +DEFINE_TRACE(sched_process_free); +DEFINE_TRACE(sched_process_exit); +DEFINE_TRACE(sched_process_wait); static void exit_mm(struct task_struct * tsk); @@ -164,7 +170,10 @@ void release_task(struct task_struct * p) int zap_leader; repeat: tracehook_prepare_release_task(p); - atomic_dec(&p->user->processes); + /* don't need to get the RCU readlock here - the process is dead and + * can't be modifying its own credentials */ + atomic_dec(&__task_cred(p)->user->processes); + proc_flush_task(p); write_lock_irq(&tasklist_lock); tracehook_finish_release_task(p); @@ -339,12 +348,12 @@ static void reparent_to_kthreadd(void) /* cpus_allowed? */ /* rt_priority? */ /* signals? */ - security_task_reparent_to_init(current); memcpy(current->signal->rlim, init_task.signal->rlim, sizeof(current->signal->rlim)); - atomic_inc(&(INIT_USER->__count)); + + atomic_inc(&init_cred.usage); + commit_creds(&init_cred); write_unlock_irq(&tasklist_lock); - switch_uid(INIT_USER); } void __set_special_pids(struct pid *pid) @@ -633,35 +642,31 @@ retry: /* * We found no owner yet mm_users > 1: this implies that we are * most likely racing with swapoff (try_to_unuse()) or /proc or - * ptrace or page migration (get_task_mm()). Mark owner as NULL, - * so that subsystems can understand the callback and take action. + * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ - down_write(&mm->mmap_sem); - cgroup_mm_owner_callbacks(mm->owner, NULL); mm->owner = NULL; - up_write(&mm->mmap_sem); return; assign_new_owner: BUG_ON(c == p); get_task_struct(c); - read_unlock(&tasklist_lock); - down_write(&mm->mmap_sem); /* * The task_lock protects c->mm from changing. * We always want mm->owner->mm == mm */ task_lock(c); + /* + * Delay read_unlock() till we have the task_lock() + * to ensure that c does not slip away underneath us + */ + read_unlock(&tasklist_lock); if (c->mm != mm) { task_unlock(c); - up_write(&mm->mmap_sem); put_task_struct(c); goto retry; } - cgroup_mm_owner_callbacks(mm->owner, c); mm->owner = c; task_unlock(c); - up_write(&mm->mmap_sem); put_task_struct(c); } #endif /* CONFIG_MM_OWNER */ @@ -1028,8 +1033,6 @@ NORET_TYPE void do_exit(long code) * task into the wait for ever nirwana as well. */ tsk->flags |= PF_EXITPIDONE; - if (tsk->io_context) - exit_io_context(); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } @@ -1048,10 +1051,7 @@ NORET_TYPE void do_exit(long code) preempt_count()); acct_update_integrals(tsk); - if (tsk->mm) { - update_hiwater_rss(tsk->mm); - update_hiwater_vm(tsk->mm); - } + group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { hrtimer_cancel(&tsk->signal->real_timer); @@ -1078,7 +1078,6 @@ NORET_TYPE void do_exit(long code) check_stack_usage(); exit_thread(); cgroup_exit(tsk, 1); - exit_keys(tsk); if (group_dead && tsk->signal->leader) disassociate_ctty(1); @@ -1123,7 +1122,6 @@ NORET_TYPE void do_exit(long code) preempt_disable(); /* causes final put_task_struct in finish_task_switch(). */ tsk->state = TASK_DEAD; - schedule(); BUG(); /* Avoid "noreturn function does return". */ @@ -1263,12 +1261,12 @@ static int wait_task_zombie(struct task_struct *p, int options, unsigned long state; int retval, status, traced; pid_t pid = task_pid_vnr(p); + uid_t uid = __task_cred(p)->uid; if (!likely(options & WEXITED)) return 0; if (unlikely(options & WNOWAIT)) { - uid_t uid = p->uid; int exit_code = p->exit_code; int why, status; @@ -1321,10 +1319,10 @@ static int wait_task_zombie(struct task_struct *p, int options, * group, which consolidates times for all threads in the * group including the group leader. */ + thread_group_cputime(p, &cputime); spin_lock_irq(&p->parent->sighand->siglock); psig = p->parent->signal; sig = p->signal; - thread_group_cputime(p, &cputime); psig->cutime = cputime_add(psig->cutime, cputime_add(cputime.utime, @@ -1389,7 +1387,7 @@ static int wait_task_zombie(struct task_struct *p, int options, if (!retval && infop) retval = put_user(pid, &infop->si_pid); if (!retval && infop) - retval = put_user(p->uid, &infop->si_uid); + retval = put_user(uid, &infop->si_uid); if (!retval) retval = pid; @@ -1454,7 +1452,8 @@ static int wait_task_stopped(int ptrace, struct task_struct *p, if (!unlikely(options & WNOWAIT)) p->exit_code = 0; - uid = p->uid; + /* don't need the RCU readlock here as we're holding a spinlock */ + uid = __task_cred(p)->uid; unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1528,10 +1527,10 @@ static int wait_task_continued(struct task_struct *p, int options, } if (!unlikely(options & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; + uid = __task_cred(p)->uid; spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); - uid = p->uid; get_task_struct(p); read_unlock(&tasklist_lock); diff --git a/kernel/extable.c b/kernel/extable.c index a26cb2e..e136ed8 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -17,6 +17,7 @@ */ #include <linux/module.h> #include <linux/init.h> +#include <linux/ftrace.h> #include <asm/uaccess.h> #include <asm/sections.h> @@ -40,7 +41,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -int core_kernel_text(unsigned long addr) +__notrace_funcgraph int core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) @@ -53,7 +54,7 @@ int core_kernel_text(unsigned long addr) return 0; } -int __kernel_text_address(unsigned long addr) +__notrace_funcgraph int __kernel_text_address(unsigned long addr) { if (core_kernel_text(addr)) return 1; @@ -66,3 +67,19 @@ int kernel_text_address(unsigned long addr) return 1; return module_text_address(addr) != NULL; } + +/* + * On some architectures (PPC64, IA64) function pointers + * are actually only tokens to some data that then holds the + * real function address. As a result, to find if a function + * pointer is part of the kernel text, we need to do some + * special dereferencing first. + */ +int func_ptr_is_kernel_text(void *ptr) +{ + unsigned long addr; + addr = (unsigned long) dereference_function_descriptor(ptr); + if (core_kernel_text(addr)) + return 1; + return module_text_address(addr) != NULL; +} diff --git a/kernel/fork.c b/kernel/fork.c index 495da2e..4018308 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -47,6 +47,7 @@ #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> +#include <linux/ftrace.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/acct.h> @@ -80,6 +81,8 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ +DEFINE_TRACE(sched_process_fork); + int nr_processes(void) { int cpu; @@ -137,6 +140,7 @@ void free_task(struct task_struct *tsk) prop_local_destroy_single(&tsk->dirties); free_thread_info(tsk->stack); rt_mutex_debug_task_free(tsk); + ftrace_graph_exit_task(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); @@ -147,9 +151,8 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); - security_task_free(tsk); - free_uid(tsk->user); - put_group_info(tsk->group_info); + put_cred(tsk->real_cred); + put_cred(tsk->cred); delayacct_tsk_free(tsk); if (!profile_handoff_task(tsk)) @@ -397,6 +400,18 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) +static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; + +static int __init coredump_filter_setup(char *s) +{ + default_dump_filter = + (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & + MMF_DUMP_FILTER_MASK; + return 1; +} + +__setup("coredump_filter=", coredump_filter_setup); + #include <linux/init_task.h> static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) @@ -405,15 +420,14 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) atomic_set(&mm->mm_count, 1); init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); - mm->flags = (current->mm) ? current->mm->flags - : MMF_DUMP_FILTER_DEFAULT; + mm->flags = (current->mm) ? current->mm->flags : default_dump_filter; mm->core_state = NULL; mm->nr_ptes = 0; set_mm_counter(mm, file_rss, 0); set_mm_counter(mm, anon_rss, 0); spin_lock_init(&mm->page_table_lock); - rwlock_init(&mm->ioctx_list_lock); - mm->ioctx_list = NULL; + spin_lock_init(&mm->ioctx_lock); + INIT_HLIST_HEAD(&mm->ioctx_list); mm->free_area_cache = TASK_UNMAPPED_BASE; mm->cached_hole_size = ~0UL; mm_init_owner(mm, p); @@ -755,7 +769,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; - if (clone_flags & (CLONE_SIGHAND | CLONE_THREAD)) { + if (clone_flags & CLONE_SIGHAND) { atomic_inc(¤t->sighand->count); return 0; } @@ -818,12 +832,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) if (!sig) return -ENOMEM; - ret = copy_thread_group_keys(tsk); - if (ret < 0) { - kmem_cache_free(signal_cachep, sig); - return ret; - } - atomic_set(&sig->count, 1); atomic_set(&sig->live, 1); init_waitqueue_head(&sig->wait_chldexit); @@ -868,7 +876,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_signal(struct signal_struct *sig) { thread_group_cputime_free(sig); - exit_thread_group_keys(sig); tty_kref_put(sig->tty); kmem_cache_free(signal_cachep, sig); } @@ -984,16 +991,16 @@ static struct task_struct *copy_process(unsigned long clone_flags, DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = -EAGAIN; - if (atomic_read(&p->user->processes) >= + if (atomic_read(&p->real_cred->user->processes) >= p->signal->rlim[RLIMIT_NPROC].rlim_cur) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && - p->user != current->nsproxy->user_ns->root_user) + p->real_cred->user != INIT_USER) goto bad_fork_free; } - atomic_inc(&p->user->__count); - atomic_inc(&p->user->processes); - get_group_info(p->group_info); + retval = copy_creds(p, clone_flags); + if (retval < 0) + goto bad_fork_free; /* * If multiple threads are within copy_process(), then this check @@ -1048,10 +1055,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, do_posix_clock_monotonic_gettime(&p->start_time); p->real_start_time = p->start_time; monotonic_to_bootbased(&p->real_start_time); -#ifdef CONFIG_SECURITY - p->security = NULL; -#endif - p->cap_bset = current->cap_bset; p->io_context = NULL; p->audit_context = NULL; cgroup_fork(p); @@ -1092,14 +1095,14 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif + if (unlikely(ptrace_reparented(current))) + ptrace_fork(p, clone_flags); /* Perform scheduler related setup. Assign this task to a CPU. */ sched_fork(p, clone_flags); - if ((retval = security_task_alloc(p))) - goto bad_fork_cleanup_policy; if ((retval = audit_alloc(p))) - goto bad_fork_cleanup_security; + goto bad_fork_cleanup_policy; /* copy all the process information */ if ((retval = copy_semundo(clone_flags, p))) goto bad_fork_cleanup_audit; @@ -1113,10 +1116,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_sighand; if ((retval = copy_mm(clone_flags, p))) goto bad_fork_cleanup_signal; - if ((retval = copy_keys(clone_flags, p))) - goto bad_fork_cleanup_mm; if ((retval = copy_namespaces(clone_flags, p))) - goto bad_fork_cleanup_keys; + goto bad_fork_cleanup_mm; if ((retval = copy_io(clone_flags, p))) goto bad_fork_cleanup_namespaces; retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); @@ -1125,17 +1126,19 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (pid != &init_struct_pid) { retval = -ENOMEM; - pid = alloc_pid(task_active_pid_ns(p)); + pid = alloc_pid(p->nsproxy->pid_ns); if (!pid) goto bad_fork_cleanup_io; if (clone_flags & CLONE_NEWPID) { - retval = pid_ns_prepare_proc(task_active_pid_ns(p)); + retval = pid_ns_prepare_proc(p->nsproxy->pid_ns); if (retval < 0) goto bad_fork_free_pid; } } + ftrace_graph_init_task(p); + p->pid = pid_nr(pid); p->tgid = p->pid; if (clone_flags & CLONE_THREAD) @@ -1144,7 +1147,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (current->nsproxy != p->nsproxy) { retval = ns_cgroup_clone(p, pid); if (retval) - goto bad_fork_free_pid; + goto bad_fork_free_graph; } p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; @@ -1237,7 +1240,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; - goto bad_fork_free_pid; + goto bad_fork_free_graph; } if (clone_flags & CLONE_THREAD) { @@ -1274,6 +1277,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, cgroup_post_fork(p); return p; +bad_fork_free_graph: + ftrace_graph_exit_task(p); bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); @@ -1281,8 +1286,6 @@ bad_fork_cleanup_io: put_io_context(p->io_context); bad_fork_cleanup_namespaces: exit_task_namespaces(p); -bad_fork_cleanup_keys: - exit_keys(p); bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); @@ -1298,8 +1301,6 @@ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); -bad_fork_cleanup_security: - security_task_free(p); bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_put(p->mempolicy); @@ -1312,9 +1313,9 @@ bad_fork_cleanup_cgroup: bad_fork_cleanup_put_domain: module_put(task_thread_info(p)->exec_domain->module); bad_fork_cleanup_count: - put_group_info(p->group_info); - atomic_dec(&p->user->processes); - free_uid(p->user); + atomic_dec(&p->cred->user->processes); + put_cred(p->real_cred); + put_cred(p->cred); bad_fork_free: free_task(p); fork_out: @@ -1358,6 +1359,21 @@ long do_fork(unsigned long clone_flags, long nr; /* + * Do some preliminary argument and permissions checking before we + * actually start allocating stuff + */ + if (clone_flags & CLONE_NEWUSER) { + if (clone_flags & CLONE_THREAD) + return -EINVAL; + /* hopefully this check will go away when userns support is + * complete + */ + if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) || + !capable(CAP_SETGID)) + return -EPERM; + } + + /* * We hope to recycle these flags after 2.6.26 */ if (unlikely(clone_flags & CLONE_STOPPED)) { @@ -1605,8 +1621,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags) err = -EINVAL; if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| - CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWUSER| - CLONE_NEWNET)) + CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET)) goto bad_unshare_out; /* diff --git a/kernel/futex.c b/kernel/futex.c index 8af1002..002aa18 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -92,11 +92,12 @@ struct futex_pi_state { * A futex_q has a woken state, just like tasks have TASK_RUNNING. * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. * The order of wakup is always to make the first condition true, then - * wake up q->waiters, then make the second condition true. + * wake up q->waiter, then make the second condition true. */ struct futex_q { struct plist_node list; - wait_queue_head_t waiters; + /* There can only be a single waiter */ + wait_queue_head_t waiter; /* Which hash list lock to use: */ spinlock_t *lock_ptr; @@ -123,24 +124,6 @@ struct futex_hash_bucket { static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS]; /* - * Take mm->mmap_sem, when futex is shared - */ -static inline void futex_lock_mm(struct rw_semaphore *fshared) -{ - if (fshared) - down_read(fshared); -} - -/* - * Release mm->mmap_sem, when the futex is shared - */ -static inline void futex_unlock_mm(struct rw_semaphore *fshared) -{ - if (fshared) - up_read(fshared); -} - -/* * We hash on the keys returned from get_futex_key (see below). */ static struct futex_hash_bucket *hash_futex(union futex_key *key) @@ -161,6 +144,48 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2) && key1->both.offset == key2->both.offset); } +/* + * Take a reference to the resource addressed by a key. + * Can be called while holding spinlocks. + * + */ +static void get_futex_key_refs(union futex_key *key) +{ + if (!key->both.ptr) + return; + + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { + case FUT_OFF_INODE: + atomic_inc(&key->shared.inode->i_count); + break; + case FUT_OFF_MMSHARED: + atomic_inc(&key->private.mm->mm_count); + break; + } +} + +/* + * Drop a reference to the resource addressed by a key. + * The hash bucket spinlock must not be held. + */ +static void drop_futex_key_refs(union futex_key *key) +{ + if (!key->both.ptr) { + /* If we're here then we tried to put a key we failed to get */ + WARN_ON_ONCE(1); + return; + } + + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { + case FUT_OFF_INODE: + iput(key->shared.inode); + break; + case FUT_OFF_MMSHARED: + mmdrop(key->private.mm); + break; + } +} + /** * get_futex_key - Get parameters which are the keys for a futex. * @uaddr: virtual address of the futex @@ -179,12 +204,10 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2) * For other futexes, it points to ¤t->mm->mmap_sem and * caller must have taken the reader lock. but NOT any spinlocks. */ -static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared, - union futex_key *key) +static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct vm_area_struct *vma; struct page *page; int err; @@ -208,100 +231,50 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared, return -EFAULT; key->private.mm = mm; key->private.address = address; + get_futex_key_refs(key); return 0; } - /* - * The futex is hashed differently depending on whether - * it's in a shared or private mapping. So check vma first. - */ - vma = find_extend_vma(mm, address); - if (unlikely(!vma)) - return -EFAULT; - /* - * Permissions. - */ - if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ)) - return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES; +again: + err = get_user_pages_fast(address, 1, 0, &page); + if (err < 0) + return err; + + lock_page(page); + if (!page->mapping) { + unlock_page(page); + put_page(page); + goto again; + } /* * Private mappings are handled in a simple way. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to - * the object not the particular process. Therefore we use - * VM_MAYSHARE here, not VM_SHARED which is restricted to shared - * mappings of _writable_ handles. + * the object not the particular process. */ - if (likely(!(vma->vm_flags & VM_MAYSHARE))) { - key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */ + if (PageAnon(page)) { + key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; - return 0; - } - - /* - * Linear file mappings are also simple. - */ - key->shared.inode = vma->vm_file->f_path.dentry->d_inode; - key->both.offset |= FUT_OFF_INODE; /* inode-based key. */ - if (likely(!(vma->vm_flags & VM_NONLINEAR))) { - key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT) - + vma->vm_pgoff); - return 0; + } else { + key->both.offset |= FUT_OFF_INODE; /* inode-based key */ + key->shared.inode = page->mapping->host; + key->shared.pgoff = page->index; } - /* - * We could walk the page table to read the non-linear - * pte, and get the page index without fetching the page - * from swap. But that's a lot of code to duplicate here - * for a rare case, so we simply fetch the page. - */ - err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL); - if (err >= 0) { - key->shared.pgoff = - page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - put_page(page); - return 0; - } - return err; -} + get_futex_key_refs(key); -/* - * Take a reference to the resource addressed by a key. - * Can be called while holding spinlocks. - * - */ -static void get_futex_key_refs(union futex_key *key) -{ - if (key->both.ptr == NULL) - return; - switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { - case FUT_OFF_INODE: - atomic_inc(&key->shared.inode->i_count); - break; - case FUT_OFF_MMSHARED: - atomic_inc(&key->private.mm->mm_count); - break; - } + unlock_page(page); + put_page(page); + return 0; } -/* - * Drop a reference to the resource addressed by a key. - * The hash bucket spinlock must not be held. - */ -static void drop_futex_key_refs(union futex_key *key) +static inline +void put_futex_key(int fshared, union futex_key *key) { - if (!key->both.ptr) - return; - switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { - case FUT_OFF_INODE: - iput(key->shared.inode); - break; - case FUT_OFF_MMSHARED: - mmdrop(key->private.mm); - break; - } + drop_futex_key_refs(key); } static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval) @@ -328,10 +301,8 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from) /* * Fault handling. - * if fshared is non NULL, current->mm->mmap_sem is already held */ -static int futex_handle_fault(unsigned long address, - struct rw_semaphore *fshared, int attempt) +static int futex_handle_fault(unsigned long address, int attempt) { struct vm_area_struct * vma; struct mm_struct *mm = current->mm; @@ -340,8 +311,7 @@ static int futex_handle_fault(unsigned long address, if (attempt > 2) return ret; - if (!fshared) - down_read(&mm->mmap_sem); + down_read(&mm->mmap_sem); vma = find_vma(mm, address); if (vma && address >= vma->vm_start && (vma->vm_flags & VM_WRITE)) { @@ -361,8 +331,7 @@ static int futex_handle_fault(unsigned long address, current->min_flt++; } } - if (!fshared) - up_read(&mm->mmap_sem); + up_read(&mm->mmap_sem); return ret; } @@ -385,6 +354,7 @@ static int refill_pi_state_cache(void) /* pi_mutex gets initialized later */ pi_state->owner = NULL; atomic_set(&pi_state->refcount, 1); + pi_state->key = FUTEX_KEY_INIT; current->pi_state_cache = pi_state; @@ -439,13 +409,20 @@ static void free_pi_state(struct futex_pi_state *pi_state) static struct task_struct * futex_find_get_task(pid_t pid) { struct task_struct *p; + const struct cred *cred = current_cred(), *pcred; rcu_read_lock(); p = find_task_by_vpid(pid); - if (!p || ((current->euid != p->euid) && (current->euid != p->uid))) + if (!p) { p = ERR_PTR(-ESRCH); - else - get_task_struct(p); + } else { + pcred = __task_cred(p); + if (cred->euid != pcred->euid && + cred->euid != pcred->uid) + p = ERR_PTR(-ESRCH); + else + get_task_struct(p); + } rcu_read_unlock(); @@ -462,7 +439,7 @@ void exit_pi_state_list(struct task_struct *curr) struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; - union futex_key key; + union futex_key key = FUTEX_KEY_INIT; if (!futex_cmpxchg_enabled) return; @@ -607,7 +584,7 @@ static void wake_futex(struct futex_q *q) * The lock in wake_up_all() is a crucial memory barrier after the * plist_del() and also before assigning to q->lock_ptr. */ - wake_up_all(&q->waiters); + wake_up(&q->waiter); /* * The waiting task can free the futex_q as soon as this is written, * without taking any locks. This must come last. @@ -719,20 +696,17 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ -static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, - int nr_wake, u32 bitset) +static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset) { struct futex_hash_bucket *hb; struct futex_q *this, *next; struct plist_head *head; - union futex_key key; + union futex_key key = FUTEX_KEY_INIT; int ret; if (!bitset) return -EINVAL; - futex_lock_mm(fshared); - ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) goto out; @@ -759,8 +733,8 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared, } spin_unlock(&hb->lock); + put_futex_key(fshared, &key); out: - futex_unlock_mm(fshared); return ret; } @@ -769,25 +743,22 @@ out: * to this virtual address: */ static int -futex_wake_op(u32 __user *uaddr1, struct rw_semaphore *fshared, - u32 __user *uaddr2, +futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op) { - union futex_key key1, key2; + union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_hash_bucket *hb1, *hb2; struct plist_head *head; struct futex_q *this, *next; int ret, op_ret, attempt = 0; retryfull: - futex_lock_mm(fshared); - ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) - goto out; + goto out_put_key1; hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); @@ -809,12 +780,12 @@ retry: * but we might get them from range checking */ ret = op_ret; - goto out; + goto out_put_keys; #endif if (unlikely(op_ret != -EFAULT)) { ret = op_ret; - goto out; + goto out_put_keys; } /* @@ -826,18 +797,12 @@ retry: */ if (attempt++) { ret = futex_handle_fault((unsigned long)uaddr2, - fshared, attempt); + attempt); if (ret) - goto out; + goto out_put_keys; goto retry; } - /* - * If we would have faulted, release mmap_sem, - * fault it in and start all over again. - */ - futex_unlock_mm(fshared); - ret = get_user(dummy, uaddr2); if (ret) return ret; @@ -872,9 +837,11 @@ retry: spin_unlock(&hb1->lock); if (hb1 != hb2) spin_unlock(&hb2->lock); +out_put_keys: + put_futex_key(fshared, &key2); +out_put_key1: + put_futex_key(fshared, &key1); out: - futex_unlock_mm(fshared); - return ret; } @@ -882,25 +849,22 @@ out: * Requeue all waiters hashed on one physical page to another * physical page. */ -static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared, - u32 __user *uaddr2, +static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2, int nr_wake, int nr_requeue, u32 *cmpval) { - union futex_key key1, key2; + union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_hash_bucket *hb1, *hb2; struct plist_head *head1; struct futex_q *this, *next; int ret, drop_count = 0; - retry: - futex_lock_mm(fshared); - +retry: ret = get_futex_key(uaddr1, fshared, &key1); if (unlikely(ret != 0)) goto out; ret = get_futex_key(uaddr2, fshared, &key2); if (unlikely(ret != 0)) - goto out; + goto out_put_key1; hb1 = hash_futex(&key1); hb2 = hash_futex(&key2); @@ -917,18 +881,12 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared, if (hb1 != hb2) spin_unlock(&hb2->lock); - /* - * If we would have faulted, release mmap_sem, fault - * it in and start all over again. - */ - futex_unlock_mm(fshared); - ret = get_user(curval, uaddr1); if (!ret) goto retry; - return ret; + goto out_put_keys; } if (curval != *cmpval) { ret = -EAGAIN; @@ -973,8 +931,11 @@ out_unlock: while (--drop_count >= 0) drop_futex_key_refs(&key1); +out_put_keys: + put_futex_key(fshared, &key2); +out_put_key1: + put_futex_key(fshared, &key1); out: - futex_unlock_mm(fshared); return ret; } @@ -983,7 +944,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) { struct futex_hash_bucket *hb; - init_waitqueue_head(&q->waiters); + init_waitqueue_head(&q->waiter); get_futex_key_refs(&q->key); hb = hash_futex(&q->key); @@ -1035,7 +996,7 @@ static int unqueue_me(struct futex_q *q) int ret = 0; /* In the common case we don't take the spinlock, which is nice. */ - retry: +retry: lock_ptr = q->lock_ptr; barrier(); if (lock_ptr != NULL) { @@ -1096,8 +1057,7 @@ static void unqueue_me_pi(struct futex_q *q) * private futexes. */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *newowner, - struct rw_semaphore *fshared) + struct task_struct *newowner, int fshared) { u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; @@ -1176,7 +1136,7 @@ retry: handle_fault: spin_unlock(q->lock_ptr); - ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++); + ret = futex_handle_fault((unsigned long)uaddr, attempt++); spin_lock(q->lock_ptr); @@ -1196,12 +1156,13 @@ handle_fault: * In case we must use restart_block to restart a futex_wait, * we encode in the 'flags' shared capability */ -#define FLAGS_SHARED 1 +#define FLAGS_SHARED 0x01 +#define FLAGS_CLOCKRT 0x02 static long futex_wait_restart(struct restart_block *restart); -static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, - u32 val, ktime_t *abs_time, u32 bitset) +static int futex_wait(u32 __user *uaddr, int fshared, + u32 val, ktime_t *abs_time, u32 bitset, int clockrt) { struct task_struct *curr = current; DECLARE_WAITQUEUE(wait, curr); @@ -1217,12 +1178,11 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, q.pi_state = NULL; q.bitset = bitset; - retry: - futex_lock_mm(fshared); - +retry: + q.key = FUTEX_KEY_INIT; ret = get_futex_key(uaddr, fshared, &q.key); if (unlikely(ret != 0)) - goto out_release_sem; + goto out; hb = queue_lock(&q); @@ -1250,12 +1210,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, if (unlikely(ret)) { queue_unlock(&q, hb); - - /* - * If we would have faulted, release mmap_sem, fault it in and - * start all over again. - */ - futex_unlock_mm(fshared); + put_futex_key(fshared, &q.key); ret = get_user(uval, uaddr); @@ -1265,18 +1220,12 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, } ret = -EWOULDBLOCK; if (uval != val) - goto out_unlock_release_sem; + goto out_unlock_put_key; /* Only actually queue if *uaddr contained val. */ queue_me(&q, hb); /* - * Now the futex is queued and we have checked the data, we - * don't want to hold mmap_sem while we sleep. - */ - futex_unlock_mm(fshared); - - /* * There might have been scheduling since the queue_me(), as we * cannot hold a spinlock across the get_user() in case it * faults, and we cannot just set TASK_INTERRUPTIBLE state when @@ -1287,7 +1236,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, /* add_wait_queue is the barrier after __set_current_state. */ __set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&q.waiters, &wait); + add_wait_queue(&q.waiter, &wait); /* * !plist_node_empty() is safe here without any lock. * q.lock_ptr != 0 is not safe, because of ordering against wakeup. @@ -1300,8 +1249,10 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, slack = current->timer_slack_ns; if (rt_task(current)) slack = 0; - hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); + hrtimer_init_on_stack(&t.timer, + clockrt ? CLOCK_REALTIME : + CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); hrtimer_init_sleeper(&t, current); hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack); @@ -1356,14 +1307,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, if (fshared) restart->futex.flags |= FLAGS_SHARED; + if (clockrt) + restart->futex.flags |= FLAGS_CLOCKRT; return -ERESTART_RESTARTBLOCK; } - out_unlock_release_sem: +out_unlock_put_key: queue_unlock(&q, hb); + put_futex_key(fshared, &q.key); - out_release_sem: - futex_unlock_mm(fshared); +out: return ret; } @@ -1371,15 +1324,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared, static long futex_wait_restart(struct restart_block *restart) { u32 __user *uaddr = (u32 __user *)restart->futex.uaddr; - struct rw_semaphore *fshared = NULL; + int fshared = 0; ktime_t t; t.tv64 = restart->futex.time; restart->fn = do_no_restart_syscall; if (restart->futex.flags & FLAGS_SHARED) - fshared = ¤t->mm->mmap_sem; + fshared = 1; return (long)futex_wait(uaddr, fshared, restart->futex.val, &t, - restart->futex.bitset); + restart->futex.bitset, + restart->futex.flags & FLAGS_CLOCKRT); } @@ -1389,7 +1343,7 @@ static long futex_wait_restart(struct restart_block *restart) * if there are waiters then it will block, it does PI, etc. (Due to * races the kernel might see a 0 value of the futex too.) */ -static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, +static int futex_lock_pi(u32 __user *uaddr, int fshared, int detect, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to = NULL; @@ -1411,17 +1365,16 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, } q.pi_state = NULL; - retry: - futex_lock_mm(fshared); - +retry: + q.key = FUTEX_KEY_INIT; ret = get_futex_key(uaddr, fshared, &q.key); if (unlikely(ret != 0)) - goto out_release_sem; + goto out; - retry_unlocked: +retry_unlocked: hb = queue_lock(&q); - retry_locked: +retry_locked: ret = lock_taken = 0; /* @@ -1442,14 +1395,14 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, */ if (unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(current))) { ret = -EDEADLK; - goto out_unlock_release_sem; + goto out_unlock_put_key; } /* * Surprise - we got the lock. Just return to userspace: */ if (unlikely(!curval)) - goto out_unlock_release_sem; + goto out_unlock_put_key; uval = curval; @@ -1485,7 +1438,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, * We took the lock due to owner died take over. */ if (unlikely(lock_taken)) - goto out_unlock_release_sem; + goto out_unlock_put_key; /* * We dont have the lock. Look up the PI state (or create it if @@ -1502,7 +1455,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, * exit to complete. */ queue_unlock(&q, hb); - futex_unlock_mm(fshared); cond_resched(); goto retry; @@ -1525,7 +1477,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, goto retry_locked; } default: - goto out_unlock_release_sem; + goto out_unlock_put_key; } } @@ -1534,12 +1486,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, */ queue_me(&q, hb); - /* - * Now the futex is queued and we have checked the data, we - * don't want to hold mmap_sem while we sleep. - */ - futex_unlock_mm(fshared); - WARN_ON(!q.pi_state); /* * Block on the PI mutex: @@ -1552,7 +1498,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, ret = ret ? 0 : -EWOULDBLOCK; } - futex_lock_mm(fshared); spin_lock(q.lock_ptr); if (!ret) { @@ -1618,44 +1563,40 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, /* Unqueue and drop the lock */ unqueue_me_pi(&q); - futex_unlock_mm(fshared); if (to) destroy_hrtimer_on_stack(&to->timer); return ret != -EINTR ? ret : -ERESTARTNOINTR; - out_unlock_release_sem: +out_unlock_put_key: queue_unlock(&q, hb); - out_release_sem: - futex_unlock_mm(fshared); +out_put_key: + put_futex_key(fshared, &q.key); +out: if (to) destroy_hrtimer_on_stack(&to->timer); return ret; - uaddr_faulted: +uaddr_faulted: /* - * We have to r/w *(int __user *)uaddr, but we can't modify it - * non-atomically. Therefore, if get_user below is not - * enough, we need to handle the fault ourselves, while - * still holding the mmap_sem. - * - * ... and hb->lock. :-) --ANK + * We have to r/w *(int __user *)uaddr, and we have to modify it + * atomically. Therefore, if we continue to fault after get_user() + * below, we need to handle the fault ourselves, while still holding + * the mmap_sem. This can occur if the uaddr is under contention as + * we have to drop the mmap_sem in order to call get_user(). */ queue_unlock(&q, hb); if (attempt++) { - ret = futex_handle_fault((unsigned long)uaddr, fshared, - attempt); + ret = futex_handle_fault((unsigned long)uaddr, attempt); if (ret) - goto out_release_sem; + goto out_put_key; goto retry_unlocked; } - futex_unlock_mm(fshared); - ret = get_user(uval, uaddr); - if (!ret && (uval != -EFAULT)) + if (!ret) goto retry; if (to) @@ -1668,13 +1609,13 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared, * This is the in-kernel slowpath: we look up the PI state (if any), * and do the rt-mutex unlock. */ -static int futex_unlock_pi(u32 __user *uaddr, struct rw_semaphore *fshared) +static int futex_unlock_pi(u32 __user *uaddr, int fshared) { struct futex_hash_bucket *hb; struct futex_q *this, *next; u32 uval; struct plist_head *head; - union futex_key key; + union futex_key key = FUTEX_KEY_INIT; int ret, attempt = 0; retry: @@ -1685,10 +1626,6 @@ retry: */ if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current)) return -EPERM; - /* - * First take all the futex related locks: - */ - futex_lock_mm(fshared); ret = get_futex_key(uaddr, fshared, &key); if (unlikely(ret != 0)) @@ -1746,35 +1683,31 @@ retry_unlocked: out_unlock: spin_unlock(&hb->lock); -out: - futex_unlock_mm(fshared); + put_futex_key(fshared, &key); +out: return ret; pi_faulted: /* - * We have to r/w *(int __user *)uaddr, but we can't modify it - * non-atomically. Therefore, if get_user below is not - * enough, we need to handle the fault ourselves, while - * still holding the mmap_sem. - * - * ... and hb->lock. --ANK + * We have to r/w *(int __user *)uaddr, and we have to modify it + * atomically. Therefore, if we continue to fault after get_user() + * below, we need to handle the fault ourselves, while still holding + * the mmap_sem. This can occur if the uaddr is under contention as + * we have to drop the mmap_sem in order to call get_user(). */ spin_unlock(&hb->lock); if (attempt++) { - ret = futex_handle_fault((unsigned long)uaddr, fshared, - attempt); + ret = futex_handle_fault((unsigned long)uaddr, attempt); if (ret) goto out; uval = 0; goto retry_unlocked; } - futex_unlock_mm(fshared); - ret = get_user(uval, uaddr); - if (!ret && (uval != -EFAULT)) + if (!ret) goto retry; return ret; @@ -1829,6 +1762,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, { struct robust_list_head __user *head; unsigned long ret; + const struct cred *cred = current_cred(), *pcred; if (!futex_cmpxchg_enabled) return -ENOSYS; @@ -1844,8 +1778,10 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, if (!p) goto err_unlock; ret = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_PTRACE)) + pcred = __task_cred(p); + if (cred->euid != pcred->euid && + cred->euid != pcred->uid && + !capable(CAP_SYS_PTRACE)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); @@ -1898,8 +1834,7 @@ retry: * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, &curr->mm->mmap_sem, 1, - FUTEX_BITSET_MATCH_ANY); + futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } @@ -1993,18 +1928,22 @@ void exit_robust_list(struct task_struct *curr) long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { - int ret = -ENOSYS; + int clockrt, ret = -ENOSYS; int cmd = op & FUTEX_CMD_MASK; - struct rw_semaphore *fshared = NULL; + int fshared = 0; if (!(op & FUTEX_PRIVATE_FLAG)) - fshared = ¤t->mm->mmap_sem; + fshared = 1; + + clockrt = op & FUTEX_CLOCK_REALTIME; + if (clockrt && cmd != FUTEX_WAIT_BITSET) + return -ENOSYS; switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; case FUTEX_WAIT_BITSET: - ret = futex_wait(uaddr, fshared, val, timeout, val3); + ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt); break; case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 04ac3a9..d607a5b 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -135,6 +135,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, { struct compat_robust_list_head __user *head; unsigned long ret; + const struct cred *cred = current_cred(), *pcred; if (!futex_cmpxchg_enabled) return -ENOSYS; @@ -150,8 +151,10 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, if (!p) goto err_unlock; ret = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_PTRACE)) + pcred = __task_cred(p); + if (cred->euid != pcred->euid && + cred->euid != pcred->uid && + !capable(CAP_SYS_PTRACE)) goto err_unlock; head = p->compat_robust_list; read_unlock(&tasklist_lock); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 47e6334..1455b76 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -32,7 +32,6 @@ */ #include <linux/cpu.h> -#include <linux/irq.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/hrtimer.h> @@ -442,22 +441,6 @@ static inline void debug_hrtimer_activate(struct hrtimer *timer) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } #endif -/* - * Check, whether the timer is on the callback pending list - */ -static inline int hrtimer_cb_pending(const struct hrtimer *timer) -{ - return timer->state & HRTIMER_STATE_PENDING; -} - -/* - * Remove a timer from the callback pending list - */ -static inline void hrtimer_remove_cb_pending(struct hrtimer *timer) -{ - list_del_init(&timer->cb_entry); -} - /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS @@ -651,6 +634,7 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { } + /* * When High resolution timers are active, try to reprogram. Note, that in case * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry @@ -661,31 +645,10 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, struct hrtimer_clock_base *base) { if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) { - - /* Timer is expired, act upon the callback mode */ - switch(timer->cb_mode) { - case HRTIMER_CB_IRQSAFE_PERCPU: - case HRTIMER_CB_IRQSAFE_UNLOCKED: - /* - * This is solely for the sched tick emulation with - * dynamic tick support to ensure that we do not - * restart the tick right on the edge and end up with - * the tick timer in the softirq ! The calling site - * takes care of this. Also used for hrtimer sleeper ! - */ - debug_hrtimer_deactivate(timer); - return 1; - case HRTIMER_CB_SOFTIRQ: - /* - * Move everything else into the softirq pending list ! - */ - list_add_tail(&timer->cb_entry, - &base->cpu_base->cb_pending); - timer->state = HRTIMER_STATE_PENDING; - return 1; - default: - BUG(); - } + spin_unlock(&base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + spin_lock(&base->cpu_base->lock); + return 1; } return 0; } @@ -724,11 +687,6 @@ static int hrtimer_switch_to_hres(void) return 1; } -static inline void hrtimer_raise_softirq(void) -{ - raise_softirq(HRTIMER_SOFTIRQ); -} - #else static inline int hrtimer_hres_active(void) { return 0; } @@ -742,12 +700,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, } static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { } static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { } -static inline int hrtimer_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) -{ - return 0; -} -static inline void hrtimer_raise_softirq(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ @@ -818,9 +770,11 @@ EXPORT_SYMBOL_GPL(hrtimer_forward); * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. + * + * Returns 1 when the new timer is the leftmost timer in the tree. */ -static void enqueue_hrtimer(struct hrtimer *timer, - struct hrtimer_clock_base *base, int reprogram) +static int enqueue_hrtimer(struct hrtimer *timer, + struct hrtimer_clock_base *base) { struct rb_node **link = &base->active.rb_node; struct rb_node *parent = NULL; @@ -852,20 +806,8 @@ static void enqueue_hrtimer(struct hrtimer *timer, * Insert the timer to the rbtree and check whether it * replaces the first pending timer */ - if (leftmost) { - /* - * Reprogram the clock event device. When the timer is already - * expired hrtimer_enqueue_reprogram has either called the - * callback or added it to the pending list and raised the - * softirq. - * - * This is a NOP for !HIGHRES - */ - if (reprogram && hrtimer_enqueue_reprogram(timer, base)) - return; - + if (leftmost) base->first = &timer->node; - } rb_link_node(&timer->node, parent, link); rb_insert_color(&timer->node, &base->active); @@ -874,6 +816,8 @@ static void enqueue_hrtimer(struct hrtimer *timer, * state of a possibly running callback. */ timer->state |= HRTIMER_STATE_ENQUEUED; + + return leftmost; } /* @@ -890,10 +834,7 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, unsigned long newstate, int reprogram) { - /* High res. callback list. NOP for !HIGHRES */ - if (hrtimer_cb_pending(timer)) - hrtimer_remove_cb_pending(timer); - else { + if (timer->state & HRTIMER_STATE_ENQUEUED) { /* * Remove the timer from the rbtree and replace the * first entry pointer if necessary. @@ -953,7 +894,7 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n { struct hrtimer_clock_base *base, *new_base; unsigned long flags; - int ret, raise; + int ret, leftmost; base = lock_hrtimer_base(timer, &flags); @@ -981,33 +922,19 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n timer_stats_hrtimer_set_start_info(timer); + leftmost = enqueue_hrtimer(timer, new_base); + /* * Only allow reprogramming if the new base is on this CPU. * (it might still be on another CPU if the timer was pending) + * + * XXX send_remote_softirq() ? */ - enqueue_hrtimer(timer, new_base, - new_base->cpu_base == &__get_cpu_var(hrtimer_bases)); - - /* - * The timer may be expired and moved to the cb_pending - * list. We can not raise the softirq with base lock held due - * to a possible deadlock with runqueue lock. - */ - raise = timer->state == HRTIMER_STATE_PENDING; - - /* - * We use preempt_disable to prevent this task from migrating after - * setting up the softirq and raising it. Otherwise, if me migrate - * we will raise the softirq on the wrong CPU. - */ - preempt_disable(); + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) + hrtimer_enqueue_reprogram(timer, new_base); unlock_hrtimer_base(timer, &flags); - if (raise) - hrtimer_raise_softirq(); - preempt_enable(); - return ret; } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); @@ -1192,75 +1119,6 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp) } EXPORT_SYMBOL_GPL(hrtimer_get_res); -static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base) -{ - spin_lock_irq(&cpu_base->lock); - - while (!list_empty(&cpu_base->cb_pending)) { - enum hrtimer_restart (*fn)(struct hrtimer *); - struct hrtimer *timer; - int restart; - int emulate_hardirq_ctx = 0; - - timer = list_entry(cpu_base->cb_pending.next, - struct hrtimer, cb_entry); - - debug_hrtimer_deactivate(timer); - timer_stats_account_hrtimer(timer); - - fn = timer->function; - /* - * A timer might have been added to the cb_pending list - * when it was migrated during a cpu-offline operation. - * Emulate hardirq context for such timers. - */ - if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU || - timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) - emulate_hardirq_ctx = 1; - - __remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0); - spin_unlock_irq(&cpu_base->lock); - - if (unlikely(emulate_hardirq_ctx)) { - local_irq_disable(); - restart = fn(timer); - local_irq_enable(); - } else - restart = fn(timer); - - spin_lock_irq(&cpu_base->lock); - - timer->state &= ~HRTIMER_STATE_CALLBACK; - if (restart == HRTIMER_RESTART) { - BUG_ON(hrtimer_active(timer)); - /* - * Enqueue the timer, allow reprogramming of the event - * device - */ - enqueue_hrtimer(timer, timer->base, 1); - } else if (hrtimer_active(timer)) { - /* - * If the timer was rearmed on another CPU, reprogram - * the event device. - */ - struct hrtimer_clock_base *base = timer->base; - - if (base->first == &timer->node && - hrtimer_reprogram(timer, base)) { - /* - * Timer is expired. Thus move it from tree to - * pending list again. - */ - __remove_hrtimer(timer, base, - HRTIMER_STATE_PENDING, 0); - list_add_tail(&timer->cb_entry, - &base->cpu_base->cb_pending); - } - } - } - spin_unlock_irq(&cpu_base->lock); -} - static void __run_hrtimer(struct hrtimer *timer) { struct hrtimer_clock_base *base = timer->base; @@ -1268,34 +1126,30 @@ static void __run_hrtimer(struct hrtimer *timer) enum hrtimer_restart (*fn)(struct hrtimer *); int restart; + WARN_ON(!irqs_disabled()); + debug_hrtimer_deactivate(timer); __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); timer_stats_account_hrtimer(timer); - fn = timer->function; - if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU || - timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) { - /* - * Used for scheduler timers, avoid lock inversion with - * rq->lock and tasklist_lock. - * - * These timers are required to deal with enqueue expiry - * themselves and are not allowed to migrate. - */ - spin_unlock(&cpu_base->lock); - restart = fn(timer); - spin_lock(&cpu_base->lock); - } else - restart = fn(timer); /* - * Note: We clear the CALLBACK bit after enqueue_hrtimer to avoid - * reprogramming of the event hardware. This happens at the end of this - * function anyway. + * Because we run timers from hardirq context, there is no chance + * they get migrated to another cpu, therefore its safe to unlock + * the timer base. + */ + spin_unlock(&cpu_base->lock); + restart = fn(timer); + spin_lock(&cpu_base->lock); + + /* + * Note: We clear the CALLBACK bit after enqueue_hrtimer and + * we do not reprogramm the event hardware. Happens either in + * hrtimer_start_range_ns() or in hrtimer_interrupt() */ if (restart != HRTIMER_NORESTART) { BUG_ON(timer->state != HRTIMER_STATE_CALLBACK); - enqueue_hrtimer(timer, base, 0); + enqueue_hrtimer(timer, base); } timer->state &= ~HRTIMER_STATE_CALLBACK; } @@ -1311,7 +1165,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); struct hrtimer_clock_base *base; ktime_t expires_next, now; - int i, raise = 0; + int i; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; @@ -1360,16 +1214,6 @@ void hrtimer_interrupt(struct clock_event_device *dev) break; } - /* Move softirq callbacks to the pending list */ - if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) { - __remove_hrtimer(timer, base, - HRTIMER_STATE_PENDING, 0); - list_add_tail(&timer->cb_entry, - &base->cpu_base->cb_pending); - raise = 1; - continue; - } - __run_hrtimer(timer); } spin_unlock(&cpu_base->lock); @@ -1383,10 +1227,22 @@ void hrtimer_interrupt(struct clock_event_device *dev) if (tick_program_event(expires_next, 0)) goto retry; } +} + +/* + * local version of hrtimer_peek_ahead_timers() called with interrupts + * disabled. + */ +static void __hrtimer_peek_ahead_timers(void) +{ + struct tick_device *td; + + if (!hrtimer_hres_active()) + return; - /* Raise softirq ? */ - if (raise) - raise_softirq(HRTIMER_SOFTIRQ); + td = &__get_cpu_var(tick_cpu_device); + if (td && td->evtdev) + hrtimer_interrupt(td->evtdev); } /** @@ -1400,25 +1256,23 @@ void hrtimer_interrupt(struct clock_event_device *dev) */ void hrtimer_peek_ahead_timers(void) { - struct tick_device *td; unsigned long flags; - if (!hrtimer_hres_active()) - return; - local_irq_save(flags); - td = &__get_cpu_var(tick_cpu_device); - if (td && td->evtdev) - hrtimer_interrupt(td->evtdev); + __hrtimer_peek_ahead_timers(); local_irq_restore(flags); } static void run_hrtimer_softirq(struct softirq_action *h) { - run_hrtimer_pending(&__get_cpu_var(hrtimer_bases)); + hrtimer_peek_ahead_timers(); } -#endif /* CONFIG_HIGH_RES_TIMERS */ +#else /* CONFIG_HIGH_RES_TIMERS */ + +static inline void __hrtimer_peek_ahead_timers(void) { } + +#endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from timer softirq every jiffy, expire hrtimers: @@ -1429,8 +1283,6 @@ static void run_hrtimer_softirq(struct softirq_action *h) */ void hrtimer_run_pending(void) { - struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); - if (hrtimer_hres_active()) return; @@ -1444,8 +1296,6 @@ void hrtimer_run_pending(void) */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) hrtimer_switch_to_hres(); - - run_hrtimer_pending(cpu_base); } /* @@ -1482,14 +1332,6 @@ void hrtimer_run_queues(void) hrtimer_get_expires_tv64(timer)) break; - if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) { - __remove_hrtimer(timer, base, - HRTIMER_STATE_PENDING, 0); - list_add_tail(&timer->cb_entry, - &base->cpu_base->cb_pending); - continue; - } - __run_hrtimer(timer); } spin_unlock(&cpu_base->lock); @@ -1516,9 +1358,6 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) { sl->timer.function = hrtimer_wakeup; sl->task = task; -#ifdef CONFIG_HIGH_RES_TIMERS - sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED; -#endif } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) @@ -1655,18 +1494,16 @@ static void __cpuinit init_hrtimers_cpu(int cpu) for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) cpu_base->clock_base[i].cpu_base = cpu_base; - INIT_LIST_HEAD(&cpu_base->cb_pending); hrtimer_init_hres(cpu_base); } #ifdef CONFIG_HOTPLUG_CPU -static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base, - struct hrtimer_clock_base *new_base, int dcpu) +static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, + struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct rb_node *node; - int raise = 0; while ((node = rb_first(&old_base->active))) { timer = rb_entry(node, struct hrtimer, node); @@ -1674,18 +1511,6 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base, debug_hrtimer_deactivate(timer); /* - * Should not happen. Per CPU timers should be - * canceled _before_ the migration code is called - */ - if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU) { - __remove_hrtimer(timer, old_base, - HRTIMER_STATE_INACTIVE, 0); - WARN(1, "hrtimer (%p %p)active but cpu %d dead\n", - timer, timer->function, dcpu); - continue; - } - - /* * Mark it as STATE_MIGRATE not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU @@ -1693,112 +1518,73 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base, __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0); timer->base = new_base; /* - * Enqueue the timer. Allow reprogramming of the event device + * Enqueue the timers on the new cpu. This does not + * reprogram the event device in case the timer + * expires before the earliest on this CPU, but we run + * hrtimer_interrupt after we migrated everything to + * sort out already expired timers and reprogram the + * event device. */ - enqueue_hrtimer(timer, new_base, 1); + enqueue_hrtimer(timer, new_base); -#ifdef CONFIG_HIGH_RES_TIMERS - /* - * Happens with high res enabled when the timer was - * already expired and the callback mode is - * HRTIMER_CB_IRQSAFE_UNLOCKED (hrtimer_sleeper). The - * enqueue code does not move them to the soft irq - * pending list for performance/latency reasons, but - * in the migration state, we need to do that - * otherwise we end up with a stale timer. - */ - if (timer->state == HRTIMER_STATE_MIGRATE) { - timer->state = HRTIMER_STATE_PENDING; - list_add_tail(&timer->cb_entry, - &new_base->cpu_base->cb_pending); - raise = 1; - } -#endif /* Clear the migration state bit */ timer->state &= ~HRTIMER_STATE_MIGRATE; } - return raise; -} - -#ifdef CONFIG_HIGH_RES_TIMERS -static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base, - struct hrtimer_cpu_base *new_base) -{ - struct hrtimer *timer; - int raise = 0; - - while (!list_empty(&old_base->cb_pending)) { - timer = list_entry(old_base->cb_pending.next, - struct hrtimer, cb_entry); - - __remove_hrtimer(timer, timer->base, HRTIMER_STATE_PENDING, 0); - timer->base = &new_base->clock_base[timer->base->index]; - list_add_tail(&timer->cb_entry, &new_base->cb_pending); - raise = 1; - } - return raise; -} -#else -static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base, - struct hrtimer_cpu_base *new_base) -{ - return 0; } -#endif -static void migrate_hrtimers(int cpu) +static void migrate_hrtimers(int scpu) { struct hrtimer_cpu_base *old_base, *new_base; - int i, raise = 0; + int i; - BUG_ON(cpu_online(cpu)); - old_base = &per_cpu(hrtimer_bases, cpu); - new_base = &get_cpu_var(hrtimer_bases); + BUG_ON(cpu_online(scpu)); + tick_cancel_sched_timer(scpu); - tick_cancel_sched_timer(cpu); + local_irq_disable(); + old_base = &per_cpu(hrtimer_bases, scpu); + new_base = &__get_cpu_var(hrtimer_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(&new_base->lock); spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { - if (migrate_hrtimer_list(&old_base->clock_base[i], - &new_base->clock_base[i], cpu)) - raise = 1; + migrate_hrtimer_list(&old_base->clock_base[i], + &new_base->clock_base[i]); } - if (migrate_hrtimer_pending(old_base, new_base)) - raise = 1; - spin_unlock(&old_base->lock); - spin_unlock_irq(&new_base->lock); - put_cpu_var(hrtimer_bases); + spin_unlock(&new_base->lock); - if (raise) - hrtimer_raise_softirq(); + /* Check, if we got expired work to do */ + __hrtimer_peek_ahead_timers(); + local_irq_enable(); } + #endif /* CONFIG_HOTPLUG_CPU */ static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { - unsigned int cpu = (long)hcpu; + int scpu = (long)hcpu; switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - init_hrtimers_cpu(cpu); + init_hrtimers_cpu(scpu); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: case CPU_DEAD_FROZEN: - clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu); - migrate_hrtimers(cpu); + { + clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu); + migrate_hrtimers(scpu); break; + } #endif default: diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 681c52d..4dd5b1e 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -3,3 +3,4 @@ obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o +obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index cc0f732..1de9700 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/delay.h> +#include <linux/async.h> #include "internals.h" @@ -34,6 +35,10 @@ unsigned long probe_irq_on(void) unsigned int status; int i; + /* + * quiesce the kernel, or at least the asynchronous portion + */ + async_synchronize_full(); mutex_lock(&probing_active); /* * something may have generated an irq long ago and we want to diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 10b5092..f63c706 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -24,9 +24,10 @@ */ void dynamic_irq_init(unsigned int irq) { - struct irq_desc *desc = irq_to_desc(irq); + struct irq_desc *desc; unsigned long flags; + desc = irq_to_desc(irq); if (!desc) { WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq); return; @@ -45,7 +46,7 @@ void dynamic_irq_init(unsigned int irq) desc->irq_count = 0; desc->irqs_unhandled = 0; #ifdef CONFIG_SMP - cpus_setall(desc->affinity); + cpumask_setall(&desc->affinity); #endif spin_unlock_irqrestore(&desc->lock, flags); } @@ -124,6 +125,7 @@ int set_irq_type(unsigned int irq, unsigned int type) return -ENODEV; } + type &= IRQ_TYPE_SENSE_MASK; if (type == IRQ_TYPE_NONE) return 0; @@ -352,6 +354,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc) spin_lock(&desc->lock); mask_ack_irq(desc, irq); + desc = irq_remap_to_desc(irq, desc); if (unlikely(desc->status & IRQ_INPROGRESS)) goto out_unlock; @@ -429,6 +432,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) desc->status &= ~IRQ_INPROGRESS; out: desc->chip->eoi(irq); + desc = irq_remap_to_desc(irq, desc); spin_unlock(&desc->lock); } @@ -465,12 +469,14 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) !desc->action)) { desc->status |= (IRQ_PENDING | IRQ_MASKED); mask_ack_irq(desc, irq); + desc = irq_remap_to_desc(irq, desc); goto out_unlock; } kstat_incr_irqs_this_cpu(irq, desc); /* Start handling the irq */ desc->chip->ack(irq); + desc = irq_remap_to_desc(irq, desc); /* Mark the IRQ currently in progress.*/ desc->status |= IRQ_INPROGRESS; @@ -531,8 +537,10 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc) if (!noirqdebug) note_interrupt(irq, desc, action_ret); - if (desc->chip->eoi) + if (desc->chip->eoi) { desc->chip->eoi(irq); + desc = irq_remap_to_desc(irq, desc); + } } void @@ -567,8 +575,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, /* Uninstall? */ if (handle == handle_bad_irq) { - if (desc->chip != &no_irq_chip) + if (desc->chip != &no_irq_chip) { mask_ack_irq(desc, irq); + desc = irq_remap_to_desc(irq, desc); + } desc->status |= IRQ_DISABLED; desc->depth = 1; } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index c815b42..c20db0b 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -15,9 +15,16 @@ #include <linux/random.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <linux/rculist.h> +#include <linux/hash.h> #include "internals.h" +/* + * lockdep: we want to handle all irq_desc locks as a single lock-class: + */ +struct lock_class_key irq_desc_lock_class; + /** * handle_bad_irq - handle spurious and unhandled irqs * @irq: the interrupt number @@ -49,6 +56,150 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc) int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); +#ifdef CONFIG_SPARSE_IRQ +static struct irq_desc irq_desc_init = { + .irq = -1, + .status = IRQ_DISABLED, + .chip = &no_irq_chip, + .handle_irq = handle_bad_irq, + .depth = 1, + .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock), +#ifdef CONFIG_SMP + .affinity = CPU_MASK_ALL +#endif +}; + +void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) +{ + unsigned long bytes; + char *ptr; + int node; + + /* Compute how many bytes we need per irq and allocate them */ + bytes = nr * sizeof(unsigned int); + + node = cpu_to_node(cpu); + ptr = kzalloc_node(bytes, GFP_ATOMIC, node); + printk(KERN_DEBUG " alloc kstat_irqs on cpu %d node %d\n", cpu, node); + + if (ptr) + desc->kstat_irqs = (unsigned int *)ptr; +} + +static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) +{ + memcpy(desc, &irq_desc_init, sizeof(struct irq_desc)); + + spin_lock_init(&desc->lock); + desc->irq = irq; +#ifdef CONFIG_SMP + desc->cpu = cpu; +#endif + lockdep_set_class(&desc->lock, &irq_desc_lock_class); + init_kstat_irqs(desc, cpu, nr_cpu_ids); + if (!desc->kstat_irqs) { + printk(KERN_ERR "can not alloc kstat_irqs\n"); + BUG_ON(1); + } + arch_init_chip_data(desc, cpu); +} + +/* + * Protect the sparse_irqs: + */ +DEFINE_SPINLOCK(sparse_irq_lock); + +struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly; + +static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = { + [0 ... NR_IRQS_LEGACY-1] = { + .irq = -1, + .status = IRQ_DISABLED, + .chip = &no_irq_chip, + .handle_irq = handle_bad_irq, + .depth = 1, + .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock), +#ifdef CONFIG_SMP + .affinity = CPU_MASK_ALL +#endif + } +}; + +/* FIXME: use bootmem alloc ...*/ +static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS]; + +int __init early_irq_init(void) +{ + struct irq_desc *desc; + int legacy_count; + int i; + + desc = irq_desc_legacy; + legacy_count = ARRAY_SIZE(irq_desc_legacy); + + for (i = 0; i < legacy_count; i++) { + desc[i].irq = i; + desc[i].kstat_irqs = kstat_irqs_legacy[i]; + lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); + + irq_desc_ptrs[i] = desc + i; + } + + for (i = legacy_count; i < NR_IRQS; i++) + irq_desc_ptrs[i] = NULL; + + return arch_early_irq_init(); +} + +struct irq_desc *irq_to_desc(unsigned int irq) +{ + return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL; +} + +struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) +{ + struct irq_desc *desc; + unsigned long flags; + int node; + + if (irq >= NR_IRQS) { + printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n", + irq, NR_IRQS); + WARN_ON(1); + return NULL; + } + + desc = irq_desc_ptrs[irq]; + if (desc) + return desc; + + spin_lock_irqsave(&sparse_irq_lock, flags); + + /* We have to check it to avoid races with another CPU */ + desc = irq_desc_ptrs[irq]; + if (desc) + goto out_unlock; + + node = cpu_to_node(cpu); + desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); + printk(KERN_DEBUG " alloc irq_desc for %d on cpu %d node %d\n", + irq, cpu, node); + if (!desc) { + printk(KERN_ERR "can not alloc irq_desc\n"); + BUG_ON(1); + } + init_one_irq_desc(irq, desc, cpu); + + irq_desc_ptrs[irq] = desc; + +out_unlock: + spin_unlock_irqrestore(&sparse_irq_lock, flags); + + return desc; +} + +#else /* !CONFIG_SPARSE_IRQ */ + struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { [0 ... NR_IRQS-1] = { .status = IRQ_DISABLED, @@ -62,6 +213,32 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { } }; +int __init early_irq_init(void) +{ + struct irq_desc *desc; + int count; + int i; + + desc = irq_desc; + count = ARRAY_SIZE(irq_desc); + + for (i = 0; i < count; i++) + desc[i].irq = i; + + return arch_early_irq_init(); +} + +struct irq_desc *irq_to_desc(unsigned int irq) +{ + return (irq < NR_IRQS) ? irq_desc + irq : NULL; +} + +struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) +{ + return irq_to_desc(irq); +} +#endif /* !CONFIG_SPARSE_IRQ */ + /* * What should we do if we get a hw irq event on an illegal vector? * Each architecture has to answer this themself. @@ -179,8 +356,11 @@ unsigned int __do_IRQ(unsigned int irq) /* * No locking required for CPU-local interrupts: */ - if (desc->chip->ack) + if (desc->chip->ack) { desc->chip->ack(irq); + /* get new one */ + desc = irq_remap_to_desc(irq, desc); + } if (likely(!(desc->status & IRQ_DISABLED))) { action_ret = handle_IRQ_event(irq, desc->action); if (!noirqdebug) @@ -191,8 +371,10 @@ unsigned int __do_IRQ(unsigned int irq) } spin_lock(&desc->lock); - if (desc->chip->ack) + if (desc->chip->ack) { desc->chip->ack(irq); + desc = irq_remap_to_desc(irq, desc); + } /* * REPLAY is when Linux resends an IRQ that was dropped earlier * WAITING is used by probe to mark irqs that are being tested @@ -259,19 +441,22 @@ out: } #endif - -#ifdef CONFIG_TRACE_IRQFLAGS -/* - * lockdep: we want to handle all irq_desc locks as a single lock-class: - */ -static struct lock_class_key irq_desc_lock_class; - void early_init_irq_lock_class(void) { struct irq_desc *desc; int i; - for_each_irq_desc(i, desc) + for_each_irq_desc(i, desc) { lockdep_set_class(&desc->lock, &irq_desc_lock_class); + } +} + +#ifdef CONFIG_SPARSE_IRQ +unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) +{ + struct irq_desc *desc = irq_to_desc(irq); + return desc ? desc->kstat_irqs[cpu] : 0; } #endif +EXPORT_SYMBOL(kstat_irqs_cpu); + diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 64c1c72..e6d0a43 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -13,6 +13,11 @@ extern void compat_irq_chip_set_default_handler(struct irq_desc *desc); extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, unsigned long flags); +extern struct lock_class_key irq_desc_lock_class; +extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr); +extern spinlock_t sparse_irq_lock; +extern struct irq_desc *irq_desc_ptrs[NR_IRQS]; + #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); extern void register_handler_proc(unsigned int irq, struct irqaction *action); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 801addd..cd0cd8d 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -16,8 +16,15 @@ #include "internals.h" #ifdef CONFIG_SMP +cpumask_var_t irq_default_affinity; -cpumask_t irq_default_affinity = CPU_MASK_ALL; +static int init_irq_default_affinity(void) +{ + alloc_cpumask_var(&irq_default_affinity, GFP_KERNEL); + cpumask_setall(irq_default_affinity); + return 0; +} +core_initcall(init_irq_default_affinity); /** * synchronize_irq - wait for pending IRQ handlers (on other CPUs) @@ -79,7 +86,7 @@ int irq_can_set_affinity(unsigned int irq) * @cpumask: cpumask * */ -int irq_set_affinity(unsigned int irq, cpumask_t cpumask) +int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; @@ -91,14 +98,14 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask) #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { - desc->affinity = cpumask; + cpumask_copy(&desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); } else { desc->status |= IRQ_MOVE_PENDING; - desc->pending_mask = cpumask; + cpumask_copy(&desc->pending_mask, cpumask); } #else - desc->affinity = cpumask; + cpumask_copy(&desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); #endif desc->status |= IRQ_AFFINITY_SET; @@ -112,26 +119,24 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask) */ int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc) { - cpumask_t mask; - if (!irq_can_set_affinity(irq)) return 0; - cpus_and(mask, cpu_online_map, irq_default_affinity); - /* * Preserve an userspace affinity setup, but make sure that * one of the targets is online. */ if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) { - if (cpus_intersects(desc->affinity, cpu_online_map)) - mask = desc->affinity; + if (cpumask_any_and(&desc->affinity, cpu_online_mask) + < nr_cpu_ids) + goto set_affinity; else desc->status &= ~IRQ_AFFINITY_SET; } - desc->affinity = mask; - desc->chip->set_affinity(irq, mask); + cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity); +set_affinity: + desc->chip->set_affinity(irq, &desc->affinity); return 0; } @@ -370,16 +375,18 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, return 0; } - ret = chip->set_type(irq, flags & IRQF_TRIGGER_MASK); + /* caller masked out all except trigger mode flags */ + ret = chip->set_type(irq, flags); if (ret) pr_err("setting trigger mode %d for irq %u failed (%pF)\n", - (int)(flags & IRQF_TRIGGER_MASK), - irq, chip->set_type); + (int)flags, irq, chip->set_type); else { + if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) + flags |= IRQ_LEVEL; /* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */ - desc->status &= ~IRQ_TYPE_SENSE_MASK; - desc->status |= flags & IRQ_TYPE_SENSE_MASK; + desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK); + desc->status |= flags; } return ret; @@ -459,7 +466,8 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { - ret = __irq_set_trigger(desc, irq, new->flags); + ret = __irq_set_trigger(desc, irq, + new->flags & IRQF_TRIGGER_MASK); if (ret) { spin_unlock_irqrestore(&desc->lock, flags); @@ -673,6 +681,18 @@ int request_irq(unsigned int irq, irq_handler_t handler, struct irq_desc *desc; int retval; + /* + * handle_IRQ_event() always ignores IRQF_DISABLED except for + * the _first_ irqaction (sigh). That can cause oopsing, but + * the behavior is classified as "will not fix" so we need to + * start nudging drivers away from using that idiom. + */ + if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) + == (IRQF_SHARED|IRQF_DISABLED)) + pr_warning("IRQ %d/%s: IRQF_DISABLED is not " + "guaranteed on shared IRQs\n", + irq, devname); + #ifdef CONFIG_LOCKDEP /* * Lockdep wants atomic interrupt handlers: diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 9db681d..bd72329 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -4,7 +4,6 @@ void move_masked_irq(int irq) { struct irq_desc *desc = irq_to_desc(irq); - cpumask_t tmp; if (likely(!(desc->status & IRQ_MOVE_PENDING))) return; @@ -19,7 +18,7 @@ void move_masked_irq(int irq) desc->status &= ~IRQ_MOVE_PENDING; - if (unlikely(cpus_empty(desc->pending_mask))) + if (unlikely(cpumask_empty(&desc->pending_mask))) return; if (!desc->chip->set_affinity) @@ -27,8 +26,6 @@ void move_masked_irq(int irq) assert_spin_locked(&desc->lock); - cpus_and(tmp, desc->pending_mask, cpu_online_map); - /* * If there was a valid mask to work with, please * do the disable, re-program, enable sequence. @@ -41,10 +38,13 @@ void move_masked_irq(int irq) * For correct operation this depends on the caller * masking the irqs. */ - if (likely(!cpus_empty(tmp))) { - desc->chip->set_affinity(irq,tmp); + if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask) + < nr_cpu_ids)) { + cpumask_and(&desc->affinity, + &desc->pending_mask, cpu_online_mask); + desc->chip->set_affinity(irq, &desc->affinity); } - cpus_clear(desc->pending_mask); + cpumask_clear(&desc->pending_mask); } void move_native_irq(int irq) diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c new file mode 100644 index 0000000..ecf765c --- /dev/null +++ b/kernel/irq/numa_migrate.c @@ -0,0 +1,119 @@ +/* + * NUMA irq-desc migration code + * + * Migrate IRQ data structures (irq_desc, chip_data, etc.) over to + * the new "home node" of the IRQ. + */ + +#include <linux/irq.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/interrupt.h> +#include <linux/kernel_stat.h> + +#include "internals.h" + +static void init_copy_kstat_irqs(struct irq_desc *old_desc, + struct irq_desc *desc, + int cpu, int nr) +{ + unsigned long bytes; + + init_kstat_irqs(desc, cpu, nr); + + if (desc->kstat_irqs != old_desc->kstat_irqs) { + /* Compute how many bytes we need per irq and allocate them */ + bytes = nr * sizeof(unsigned int); + + memcpy(desc->kstat_irqs, old_desc->kstat_irqs, bytes); + } +} + +static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc) +{ + if (old_desc->kstat_irqs == desc->kstat_irqs) + return; + + kfree(old_desc->kstat_irqs); + old_desc->kstat_irqs = NULL; +} + +static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, + struct irq_desc *desc, int cpu) +{ + memcpy(desc, old_desc, sizeof(struct irq_desc)); + spin_lock_init(&desc->lock); + desc->cpu = cpu; + lockdep_set_class(&desc->lock, &irq_desc_lock_class); + init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids); + arch_init_copy_chip_data(old_desc, desc, cpu); +} + +static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc) +{ + free_kstat_irqs(old_desc, desc); + arch_free_chip_data(old_desc, desc); +} + +static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, + int cpu) +{ + struct irq_desc *desc; + unsigned int irq; + unsigned long flags; + int node; + + irq = old_desc->irq; + + spin_lock_irqsave(&sparse_irq_lock, flags); + + /* We have to check it to avoid races with another CPU */ + desc = irq_desc_ptrs[irq]; + + if (desc && old_desc != desc) + goto out_unlock; + + node = cpu_to_node(cpu); + desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); + if (!desc) { + printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq); + /* still use old one */ + desc = old_desc; + goto out_unlock; + } + init_copy_one_irq_desc(irq, old_desc, desc, cpu); + + irq_desc_ptrs[irq] = desc; + + /* free the old one */ + free_one_irq_desc(old_desc, desc); + kfree(old_desc); + +out_unlock: + spin_unlock_irqrestore(&sparse_irq_lock, flags); + + return desc; +} + +struct irq_desc *move_irq_desc(struct irq_desc *desc, int cpu) +{ + int old_cpu; + int node, old_node; + + /* those all static, do move them */ + if (desc->irq < NR_IRQS_LEGACY) + return desc; + + old_cpu = desc->cpu; + if (old_cpu != cpu) { + node = cpu_to_node(cpu); + old_node = cpu_to_node(old_cpu); + if (old_node != node) + desc = __real_move_irq_desc(desc, cpu); + else + desc->cpu = cpu; + } + + return desc; +} + diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index d257e7d..aae3f74 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -20,7 +20,7 @@ static struct proc_dir_entry *root_irq_dir; static int irq_affinity_proc_show(struct seq_file *m, void *v) { struct irq_desc *desc = irq_to_desc((long)m->private); - cpumask_t *mask = &desc->affinity; + const struct cpumask *mask = &desc->affinity; #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PENDING) @@ -40,33 +40,42 @@ static ssize_t irq_affinity_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { unsigned int irq = (int)(long)PDE(file->f_path.dentry->d_inode)->data; - cpumask_t new_value; + cpumask_var_t new_value; int err; if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity || irq_balancing_disabled(irq)) return -EIO; + if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) + return -ENOMEM; + err = cpumask_parse_user(buffer, count, new_value); if (err) - return err; + goto free_cpumask; - if (!is_affinity_mask_valid(new_value)) - return -EINVAL; + if (!is_affinity_mask_valid(new_value)) { + err = -EINVAL; + goto free_cpumask; + } /* * Do not allow disabling IRQs completely - it's a too easy * way to make the system unusable accidentally :-) At least * one online CPU still has to be targeted. */ - if (!cpus_intersects(new_value, cpu_online_map)) + if (!cpumask_intersects(new_value, cpu_online_mask)) { /* Special case for empty set - allow the architecture code to set default SMP affinity. */ - return irq_select_affinity_usr(irq) ? -EINVAL : count; - - irq_set_affinity(irq, new_value); + err = irq_select_affinity_usr(irq) ? -EINVAL : count; + } else { + irq_set_affinity(irq, new_value); + err = count; + } - return count; +free_cpumask: + free_cpumask_var(new_value); + return err; } static int irq_affinity_proc_open(struct inode *inode, struct file *file) @@ -84,7 +93,7 @@ static const struct file_operations irq_affinity_proc_fops = { static int default_affinity_show(struct seq_file *m, void *v) { - seq_cpumask(m, &irq_default_affinity); + seq_cpumask(m, irq_default_affinity); seq_putc(m, '\n'); return 0; } @@ -92,27 +101,37 @@ static int default_affinity_show(struct seq_file *m, void *v) static ssize_t default_affinity_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - cpumask_t new_value; + cpumask_var_t new_value; int err; + if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) + return -ENOMEM; + err = cpumask_parse_user(buffer, count, new_value); if (err) - return err; + goto out; - if (!is_affinity_mask_valid(new_value)) - return -EINVAL; + if (!is_affinity_mask_valid(new_value)) { + err = -EINVAL; + goto out; + } /* * Do not allow disabling IRQs completely - it's a too easy * way to make the system unusable accidentally :-) At least * one online CPU still has to be targeted. */ - if (!cpus_intersects(new_value, cpu_online_map)) - return -EINVAL; + if (!cpumask_intersects(new_value, cpu_online_mask)) { + err = -EINVAL; + goto out; + } - irq_default_affinity = new_value; + cpumask_copy(irq_default_affinity, new_value); + err = count; - return count; +out: + free_cpumask_var(new_value); + return err; } static int default_affinity_open(struct inode *inode, struct file *file) @@ -243,7 +262,11 @@ void init_irq_proc(void) /* * Create entries for all existing IRQs. */ - for_each_irq_desc(irq, desc) + for_each_irq_desc(irq, desc) { + if (!desc) + continue; + register_irq_proc(irq, desc); + } } diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 7b8b0f2..e694afa 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -30,20 +30,19 @@ #define all_var 0 #endif -/* These will be re-linked against their real values during the second link stage */ -extern const unsigned long kallsyms_addresses[] __attribute__((weak)); -extern const u8 kallsyms_names[] __attribute__((weak)); +extern const unsigned long kallsyms_addresses[]; +extern const u8 kallsyms_names[]; /* tell the compiler that the count isn't in the small data section if the arch * has one (eg: FRV) */ extern const unsigned long kallsyms_num_syms -__attribute__((weak, section(".rodata"))); + __attribute__((__section__(".rodata"))); -extern const u8 kallsyms_token_table[] __attribute__((weak)); -extern const u16 kallsyms_token_index[] __attribute__((weak)); +extern const u8 kallsyms_token_table[]; +extern const u16 kallsyms_token_index[]; -extern const unsigned long kallsyms_markers[] __attribute__((weak)); +extern const unsigned long kallsyms_markers[]; static inline int is_kernel_inittext(unsigned long addr) { @@ -168,9 +167,6 @@ static unsigned long get_symbol_pos(unsigned long addr, unsigned long symbol_start = 0, symbol_end = 0; unsigned long i, low, high, mid; - /* This kernel should never had been booted. */ - BUG_ON(!kallsyms_addresses); - /* do a binary search on the sorted kallsyms_addresses array */ low = 0; high = kallsyms_num_syms; diff --git a/kernel/kexec.c b/kernel/kexec.c index ac0fde7..3fb855a 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1116,7 +1116,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu) struct elf_prstatus prstatus; u32 *buf; - if ((cpu < 0) || (cpu >= NR_CPUS)) + if ((cpu < 0) || (cpu >= nr_cpu_ids)) return; /* Using ELF notes here is opportunistic. diff --git a/kernel/kmod.c b/kernel/kmod.c index 3d3c3ea..a27a5f6 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -51,8 +51,8 @@ char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe"; /** * request_module - try to load a kernel module - * @fmt: printf style format string for the name of the module - * @varargs: arguements as specified in the format string + * @fmt: printf style format string for the name of the module + * @...: arguments as specified in the format string * * Load a module using the user mode module loader. The function returns * zero on success or a negative errno code on failure. Note that a @@ -118,10 +118,10 @@ EXPORT_SYMBOL(request_module); struct subprocess_info { struct work_struct work; struct completion *complete; + struct cred *cred; char *path; char **argv; char **envp; - struct key *ring; enum umh_wait wait; int retval; struct file *stdin; @@ -134,19 +134,20 @@ struct subprocess_info { static int ____call_usermodehelper(void *data) { struct subprocess_info *sub_info = data; - struct key *new_session, *old_session; int retval; - /* Unblock all signals and set the session keyring. */ - new_session = key_get(sub_info->ring); + BUG_ON(atomic_read(&sub_info->cred->usage) != 1); + + /* Unblock all signals */ spin_lock_irq(¤t->sighand->siglock); - old_session = __install_session_keyring(current, new_session); flush_signal_handlers(current, 1); sigemptyset(¤t->blocked); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - key_put(old_session); + /* Install the credentials */ + commit_creds(sub_info->cred); + sub_info->cred = NULL; /* Install input pipe when needed */ if (sub_info->stdin) { @@ -185,6 +186,8 @@ void call_usermodehelper_freeinfo(struct subprocess_info *info) { if (info->cleanup) (*info->cleanup)(info->argv, info->envp); + if (info->cred) + put_cred(info->cred); kfree(info); } EXPORT_SYMBOL(call_usermodehelper_freeinfo); @@ -240,6 +243,8 @@ static void __call_usermodehelper(struct work_struct *work) pid_t pid; enum umh_wait wait = sub_info->wait; + BUG_ON(atomic_read(&sub_info->cred->usage) != 1); + /* CLONE_VFORK: wait until the usermode helper has execve'd * successfully We need the data structures to stay around * until that is done. */ @@ -362,6 +367,9 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, sub_info->path = path; sub_info->argv = argv; sub_info->envp = envp; + sub_info->cred = prepare_usermodehelper_creds(); + if (!sub_info->cred) + return NULL; out: return sub_info; @@ -376,7 +384,13 @@ EXPORT_SYMBOL(call_usermodehelper_setup); void call_usermodehelper_setkeys(struct subprocess_info *info, struct key *session_keyring) { - info->ring = session_keyring; +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred = info->cred->tgcred; + key_put(tgcred->session_keyring); + tgcred->session_keyring = key_get(session_keyring); +#else + BUG(); +#endif } EXPORT_SYMBOL(call_usermodehelper_setkeys); @@ -444,6 +458,8 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, DECLARE_COMPLETION_ONSTACK(done); int retval = 0; + BUG_ON(atomic_read(&sub_info->cred->usage) != 1); + helper_lock(); if (sub_info->path[0] == '\0') goto out; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9f8a3f2..1b9cbdc 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -69,7 +69,7 @@ static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; /* NOTE: change this value only with kprobe_mutex held */ static bool kprobe_enabled; -DEFINE_MUTEX(kprobe_mutex); /* Protects kprobe_table */ +static DEFINE_MUTEX(kprobe_mutex); /* Protects kprobe_table */ static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; static struct { spinlock_t lock ____cacheline_aligned_in_smp; @@ -115,6 +115,7 @@ enum kprobe_slot_state { SLOT_USED = 2, }; +static DEFINE_MUTEX(kprobe_insn_mutex); /* Protects kprobe_insn_pages */ static struct hlist_head kprobe_insn_pages; static int kprobe_garbage_slots; static int collect_garbage_slots(void); @@ -144,10 +145,10 @@ loop_end: } /** - * get_insn_slot() - Find a slot on an executable page for an instruction. + * __get_insn_slot() - Find a slot on an executable page for an instruction. * We allocate an executable page if there's no room on existing ones. */ -kprobe_opcode_t __kprobes *get_insn_slot(void) +static kprobe_opcode_t __kprobes *__get_insn_slot(void) { struct kprobe_insn_page *kip; struct hlist_node *pos; @@ -196,6 +197,15 @@ kprobe_opcode_t __kprobes *get_insn_slot(void) return kip->insns; } +kprobe_opcode_t __kprobes *get_insn_slot(void) +{ + kprobe_opcode_t *ret; + mutex_lock(&kprobe_insn_mutex); + ret = __get_insn_slot(); + mutex_unlock(&kprobe_insn_mutex); + return ret; +} + /* Return 1 if all garbages are collected, otherwise 0. */ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx) { @@ -226,9 +236,13 @@ static int __kprobes collect_garbage_slots(void) { struct kprobe_insn_page *kip; struct hlist_node *pos, *next; + int safety; /* Ensure no-one is preepmted on the garbages */ - if (check_safety() != 0) + mutex_unlock(&kprobe_insn_mutex); + safety = check_safety(); + mutex_lock(&kprobe_insn_mutex); + if (safety != 0) return -EAGAIN; hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) { @@ -251,6 +265,7 @@ void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) struct kprobe_insn_page *kip; struct hlist_node *pos; + mutex_lock(&kprobe_insn_mutex); hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) { if (kip->insns <= slot && slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) { @@ -267,6 +282,8 @@ void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty) if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE) collect_garbage_slots(); + + mutex_unlock(&kprobe_insn_mutex); } #endif @@ -310,7 +327,7 @@ static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { - if (kp->pre_handler) { + if (kp->pre_handler && !kprobe_gone(kp)) { set_kprobe_instance(kp); if (kp->pre_handler(kp, regs)) return 1; @@ -326,7 +343,7 @@ static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs, struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { - if (kp->post_handler) { + if (kp->post_handler && !kprobe_gone(kp)) { set_kprobe_instance(kp); kp->post_handler(kp, regs, flags); reset_kprobe_instance(); @@ -393,7 +410,7 @@ void __kprobes recycle_rp_inst(struct kretprobe_instance *ri, hlist_add_head(&ri->hlist, head); } -void kretprobe_hash_lock(struct task_struct *tsk, +void __kprobes kretprobe_hash_lock(struct task_struct *tsk, struct hlist_head **head, unsigned long *flags) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); @@ -404,13 +421,15 @@ void kretprobe_hash_lock(struct task_struct *tsk, spin_lock_irqsave(hlist_lock, *flags); } -static void kretprobe_table_lock(unsigned long hash, unsigned long *flags) +static void __kprobes kretprobe_table_lock(unsigned long hash, + unsigned long *flags) { spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); spin_lock_irqsave(hlist_lock, *flags); } -void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags) +void __kprobes kretprobe_hash_unlock(struct task_struct *tsk, + unsigned long *flags) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); spinlock_t *hlist_lock; @@ -419,7 +438,7 @@ void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags) spin_unlock_irqrestore(hlist_lock, *flags); } -void kretprobe_table_unlock(unsigned long hash, unsigned long *flags) +void __kprobes kretprobe_table_unlock(unsigned long hash, unsigned long *flags) { spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); spin_unlock_irqrestore(hlist_lock, *flags); @@ -526,9 +545,10 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p) ap->addr = p->addr; ap->pre_handler = aggr_pre_handler; ap->fault_handler = aggr_fault_handler; - if (p->post_handler) + /* We don't care the kprobe which has gone. */ + if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; - if (p->break_handler) + if (p->break_handler && !kprobe_gone(p)) ap->break_handler = aggr_break_handler; INIT_LIST_HEAD(&ap->list); @@ -547,17 +567,41 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p, int ret = 0; struct kprobe *ap; + if (kprobe_gone(old_p)) { + /* + * Attempting to insert new probe at the same location that + * had a probe in the module vaddr area which already + * freed. So, the instruction slot has already been + * released. We need a new slot for the new probe. + */ + ret = arch_prepare_kprobe(old_p); + if (ret) + return ret; + } if (old_p->pre_handler == aggr_pre_handler) { copy_kprobe(old_p, p); ret = add_new_kprobe(old_p, p); + ap = old_p; } else { ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL); - if (!ap) + if (!ap) { + if (kprobe_gone(old_p)) + arch_remove_kprobe(old_p); return -ENOMEM; + } add_aggr_kprobe(ap, old_p); copy_kprobe(ap, p); ret = add_new_kprobe(ap, p); } + if (kprobe_gone(old_p)) { + /* + * If the old_p has gone, its breakpoint has been disarmed. + * We have to arm it again after preparing real kprobes. + */ + ap->flags &= ~KPROBE_FLAG_GONE; + if (kprobe_enabled) + arch_arm_kprobe(ap); + } return ret; } @@ -600,8 +644,7 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p) return (kprobe_opcode_t *)(((char *)addr) + p->offset); } -static int __kprobes __register_kprobe(struct kprobe *p, - unsigned long called_from) +int __kprobes register_kprobe(struct kprobe *p) { int ret = 0; struct kprobe *old_p; @@ -620,28 +663,30 @@ static int __kprobes __register_kprobe(struct kprobe *p, return -EINVAL; } - p->mod_refcounted = 0; - + p->flags = 0; /* * Check if are we probing a module. */ probed_mod = __module_text_address((unsigned long) p->addr); if (probed_mod) { - struct module *calling_mod; - calling_mod = __module_text_address(called_from); /* - * We must allow modules to probe themself and in this case - * avoid incrementing the module refcount, so as to allow - * unloading of self probing modules. + * We must hold a refcount of the probed module while updating + * its code to prohibit unexpected unloading. */ - if (calling_mod && calling_mod != probed_mod) { - if (unlikely(!try_module_get(probed_mod))) { - preempt_enable(); - return -EINVAL; - } - p->mod_refcounted = 1; - } else - probed_mod = NULL; + if (unlikely(!try_module_get(probed_mod))) { + preempt_enable(); + return -EINVAL; + } + /* + * If the module freed .init.text, we couldn't insert + * kprobes in there. + */ + if (within_module_init((unsigned long)p->addr, probed_mod) && + probed_mod->state != MODULE_STATE_COMING) { + module_put(probed_mod); + preempt_enable(); + return -EINVAL; + } } preempt_enable(); @@ -668,8 +713,9 @@ static int __kprobes __register_kprobe(struct kprobe *p, out: mutex_unlock(&kprobe_mutex); - if (ret && probed_mod) + if (probed_mod) module_put(probed_mod); + return ret; } @@ -697,16 +743,16 @@ valid_p: list_is_singular(&old_p->list))) { /* * Only probe on the hash list. Disarm only if kprobes are - * enabled - otherwise, the breakpoint would already have - * been removed. We save on flushing icache. + * enabled and not gone - otherwise, the breakpoint would + * already have been removed. We save on flushing icache. */ - if (kprobe_enabled) + if (kprobe_enabled && !kprobe_gone(old_p)) arch_disarm_kprobe(p); hlist_del_rcu(&old_p->hlist); } else { - if (p->break_handler) + if (p->break_handler && !kprobe_gone(p)) old_p->break_handler = NULL; - if (p->post_handler) { + if (p->post_handler && !kprobe_gone(p)) { list_for_each_entry_rcu(list_p, &old_p->list, list) { if ((list_p != p) && (list_p->post_handler)) goto noclean; @@ -721,39 +767,27 @@ noclean: static void __kprobes __unregister_kprobe_bottom(struct kprobe *p) { - struct module *mod; struct kprobe *old_p; - if (p->mod_refcounted) { - /* - * Since we've already incremented refcount, - * we don't need to disable preemption. - */ - mod = module_text_address((unsigned long)p->addr); - if (mod) - module_put(mod); - } - - if (list_empty(&p->list) || list_is_singular(&p->list)) { - if (!list_empty(&p->list)) { - /* "p" is the last child of an aggr_kprobe */ - old_p = list_entry(p->list.next, struct kprobe, list); - list_del(&p->list); - kfree(old_p); - } + if (list_empty(&p->list)) arch_remove_kprobe(p); + else if (list_is_singular(&p->list)) { + /* "p" is the last child of an aggr_kprobe */ + old_p = list_entry(p->list.next, struct kprobe, list); + list_del(&p->list); + arch_remove_kprobe(old_p); + kfree(old_p); } } -static int __register_kprobes(struct kprobe **kps, int num, - unsigned long called_from) +int __kprobes register_kprobes(struct kprobe **kps, int num) { int i, ret = 0; if (num <= 0) return -EINVAL; for (i = 0; i < num; i++) { - ret = __register_kprobe(kps[i], called_from); + ret = register_kprobe(kps[i]); if (ret < 0) { if (i > 0) unregister_kprobes(kps, i); @@ -763,26 +797,11 @@ static int __register_kprobes(struct kprobe **kps, int num, return ret; } -/* - * Registration and unregistration functions for kprobe. - */ -int __kprobes register_kprobe(struct kprobe *p) -{ - return __register_kprobes(&p, 1, - (unsigned long)__builtin_return_address(0)); -} - void __kprobes unregister_kprobe(struct kprobe *p) { unregister_kprobes(&p, 1); } -int __kprobes register_kprobes(struct kprobe **kps, int num) -{ - return __register_kprobes(kps, num, - (unsigned long)__builtin_return_address(0)); -} - void __kprobes unregister_kprobes(struct kprobe **kps, int num) { int i; @@ -811,8 +830,7 @@ unsigned long __weak arch_deref_entry_point(void *entry) return (unsigned long)entry; } -static int __register_jprobes(struct jprobe **jps, int num, - unsigned long called_from) +int __kprobes register_jprobes(struct jprobe **jps, int num) { struct jprobe *jp; int ret = 0, i; @@ -830,7 +848,7 @@ static int __register_jprobes(struct jprobe **jps, int num, /* Todo: Verify probepoint is a function entry point */ jp->kp.pre_handler = setjmp_pre_handler; jp->kp.break_handler = longjmp_break_handler; - ret = __register_kprobe(&jp->kp, called_from); + ret = register_kprobe(&jp->kp); } if (ret < 0) { if (i > 0) @@ -843,8 +861,7 @@ static int __register_jprobes(struct jprobe **jps, int num, int __kprobes register_jprobe(struct jprobe *jp) { - return __register_jprobes(&jp, 1, - (unsigned long)__builtin_return_address(0)); + return register_jprobes(&jp, 1); } void __kprobes unregister_jprobe(struct jprobe *jp) @@ -852,12 +869,6 @@ void __kprobes unregister_jprobe(struct jprobe *jp) unregister_jprobes(&jp, 1); } -int __kprobes register_jprobes(struct jprobe **jps, int num) -{ - return __register_jprobes(jps, num, - (unsigned long)__builtin_return_address(0)); -} - void __kprobes unregister_jprobes(struct jprobe **jps, int num) { int i; @@ -920,8 +931,7 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p, return 0; } -static int __kprobes __register_kretprobe(struct kretprobe *rp, - unsigned long called_from) +int __kprobes register_kretprobe(struct kretprobe *rp) { int ret = 0; struct kretprobe_instance *inst; @@ -967,21 +977,20 @@ static int __kprobes __register_kretprobe(struct kretprobe *rp, rp->nmissed = 0; /* Establish function entry probe point */ - ret = __register_kprobe(&rp->kp, called_from); + ret = register_kprobe(&rp->kp); if (ret != 0) free_rp_inst(rp); return ret; } -static int __register_kretprobes(struct kretprobe **rps, int num, - unsigned long called_from) +int __kprobes register_kretprobes(struct kretprobe **rps, int num) { int ret = 0, i; if (num <= 0) return -EINVAL; for (i = 0; i < num; i++) { - ret = __register_kretprobe(rps[i], called_from); + ret = register_kretprobe(rps[i]); if (ret < 0) { if (i > 0) unregister_kretprobes(rps, i); @@ -991,23 +1000,11 @@ static int __register_kretprobes(struct kretprobe **rps, int num, return ret; } -int __kprobes register_kretprobe(struct kretprobe *rp) -{ - return __register_kretprobes(&rp, 1, - (unsigned long)__builtin_return_address(0)); -} - void __kprobes unregister_kretprobe(struct kretprobe *rp) { unregister_kretprobes(&rp, 1); } -int __kprobes register_kretprobes(struct kretprobe **rps, int num) -{ - return __register_kretprobes(rps, num, - (unsigned long)__builtin_return_address(0)); -} - void __kprobes unregister_kretprobes(struct kretprobe **rps, int num) { int i; @@ -1055,6 +1052,72 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p, #endif /* CONFIG_KRETPROBES */ +/* Set the kprobe gone and remove its instruction buffer. */ +static void __kprobes kill_kprobe(struct kprobe *p) +{ + struct kprobe *kp; + p->flags |= KPROBE_FLAG_GONE; + if (p->pre_handler == aggr_pre_handler) { + /* + * If this is an aggr_kprobe, we have to list all the + * chained probes and mark them GONE. + */ + list_for_each_entry_rcu(kp, &p->list, list) + kp->flags |= KPROBE_FLAG_GONE; + p->post_handler = NULL; + p->break_handler = NULL; + } + /* + * Here, we can remove insn_slot safely, because no thread calls + * the original probed function (which will be freed soon) any more. + */ + arch_remove_kprobe(p); +} + +/* Module notifier call back, checking kprobes on the module */ +static int __kprobes kprobes_module_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + struct hlist_head *head; + struct hlist_node *node; + struct kprobe *p; + unsigned int i; + int checkcore = (val == MODULE_STATE_GOING); + + if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) + return NOTIFY_DONE; + + /* + * When MODULE_STATE_GOING was notified, both of module .text and + * .init.text sections would be freed. When MODULE_STATE_LIVE was + * notified, only .init.text section would be freed. We need to + * disable kprobes which have been inserted in the sections. + */ + mutex_lock(&kprobe_mutex); + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, node, head, hlist) + if (within_module_init((unsigned long)p->addr, mod) || + (checkcore && + within_module_core((unsigned long)p->addr, mod))) { + /* + * The vaddr this probe is installed will soon + * be vfreed buy not synced to disk. Hence, + * disarming the breakpoint isn't needed. + */ + kill_kprobe(p); + } + } + mutex_unlock(&kprobe_mutex); + return NOTIFY_DONE; +} + +static struct notifier_block kprobe_module_nb = { + .notifier_call = kprobes_module_callback, + .priority = 0 +}; + static int __init init_kprobes(void) { int i, err = 0; @@ -1111,6 +1174,9 @@ static int __init init_kprobes(void) err = arch_init_kprobes(); if (!err) err = register_die_notifier(&kprobe_exceptions_nb); + if (!err) + err = register_module_notifier(&kprobe_module_nb); + kprobes_initialized = (err == 0); if (!err) @@ -1131,10 +1197,12 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, else kprobe_type = "k"; if (sym) - seq_printf(pi, "%p %s %s+0x%x %s\n", p->addr, kprobe_type, - sym, offset, (modname ? modname : " ")); + seq_printf(pi, "%p %s %s+0x%x %s %s\n", p->addr, kprobe_type, + sym, offset, (modname ? modname : " "), + (kprobe_gone(p) ? "[GONE]" : "")); else - seq_printf(pi, "%p %s %p\n", p->addr, kprobe_type, p->addr); + seq_printf(pi, "%p %s %p %s\n", p->addr, kprobe_type, p->addr, + (kprobe_gone(p) ? "[GONE]" : "")); } static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) @@ -1215,7 +1283,8 @@ static void __kprobes enable_all_kprobes(void) for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) - arch_arm_kprobe(p); + if (!kprobe_gone(p)) + arch_arm_kprobe(p); } kprobe_enabled = true; @@ -1244,7 +1313,7 @@ static void __kprobes disable_all_kprobes(void) for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { - if (!arch_trampoline_kprobe(p)) + if (!arch_trampoline_kprobe(p) && !kprobe_gone(p)) arch_disarm_kprobe(p); } } diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 08dd8ed..528dd78 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -24,7 +24,7 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) static struct kobj_attribute _name##_attr = \ __ATTR(_name, 0644, _name##_show, _name##_store) -#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET) +#if defined(CONFIG_HOTPLUG) /* current uevent sequence number */ static ssize_t uevent_seqnum_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -137,7 +137,7 @@ struct kobject *kernel_kobj; EXPORT_SYMBOL_GPL(kernel_kobj); static struct attribute * kernel_attrs[] = { -#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET) +#if defined(CONFIG_HOTPLUG) &uevent_seqnum_attr.attr, &uevent_helper_attr.attr, #endif diff --git a/kernel/kthread.c b/kernel/kthread.c index 8e7a7ce..4fbc456 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -21,6 +21,9 @@ static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; +DEFINE_TRACE(sched_kthread_stop); +DEFINE_TRACE(sched_kthread_stop_ret); + struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 46a4041..06b0c35 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -25,6 +25,7 @@ * Thanks to Arjan van de Ven for coming up with the initial idea of * mapping lock dependencies runtime. */ +#define DISABLE_BRANCH_PROFILING #include <linux/mutex.h> #include <linux/sched.h> #include <linux/delay.h> @@ -136,16 +137,16 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock) #ifdef CONFIG_LOCK_STAT static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats); -static int lock_contention_point(struct lock_class *class, unsigned long ip) +static int lock_point(unsigned long points[], unsigned long ip) { int i; - for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) { - if (class->contention_point[i] == 0) { - class->contention_point[i] = ip; + for (i = 0; i < LOCKSTAT_POINTS; i++) { + if (points[i] == 0) { + points[i] = ip; break; } - if (class->contention_point[i] == ip) + if (points[i] == ip) break; } @@ -185,6 +186,9 @@ struct lock_class_stats lock_stats(struct lock_class *class) for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++) stats.contention_point[i] += pcs->contention_point[i]; + for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++) + stats.contending_point[i] += pcs->contending_point[i]; + lock_time_add(&pcs->read_waittime, &stats.read_waittime); lock_time_add(&pcs->write_waittime, &stats.write_waittime); @@ -209,6 +213,7 @@ void clear_lock_stats(struct lock_class *class) memset(cpu_stats, 0, sizeof(struct lock_class_stats)); } memset(class->contention_point, 0, sizeof(class->contention_point)); + memset(class->contending_point, 0, sizeof(class->contending_point)); } static struct lock_class_stats *get_lock_stats(struct lock_class *class) @@ -287,14 +292,12 @@ void lockdep_off(void) { current->lockdep_recursion++; } - EXPORT_SYMBOL(lockdep_off); void lockdep_on(void) { current->lockdep_recursion--; } - EXPORT_SYMBOL(lockdep_on); /* @@ -576,7 +579,8 @@ static void print_lock_class_header(struct lock_class *class, int depth) /* * printk all lock dependencies starting at <entry>: */ -static void print_lock_dependencies(struct lock_class *class, int depth) +static void __used +print_lock_dependencies(struct lock_class *class, int depth) { struct lock_list *entry; @@ -2508,7 +2512,6 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, if (subclass) register_lock_class(lock, subclass, 1); } - EXPORT_SYMBOL_GPL(lockdep_init_map); /* @@ -2689,8 +2692,9 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock, } static int -__lock_set_subclass(struct lockdep_map *lock, - unsigned int subclass, unsigned long ip) +__lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip) { struct task_struct *curr = current; struct held_lock *hlock, *prev_hlock; @@ -2717,6 +2721,7 @@ __lock_set_subclass(struct lockdep_map *lock, return print_unlock_inbalance_bug(curr, lock, ip); found_it: + lockdep_init_map(lock, name, key, 0); class = register_lock_class(lock, subclass, 0); hlock->class_idx = class - lock_classes + 1; @@ -2901,9 +2906,9 @@ static void check_flags(unsigned long flags) #endif } -void -lock_set_subclass(struct lockdep_map *lock, - unsigned int subclass, unsigned long ip) +void lock_set_class(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, unsigned int subclass, + unsigned long ip) { unsigned long flags; @@ -2913,13 +2918,12 @@ lock_set_subclass(struct lockdep_map *lock, raw_local_irq_save(flags); current->lockdep_recursion = 1; check_flags(flags); - if (__lock_set_subclass(lock, subclass, ip)) + if (__lock_set_class(lock, name, key, subclass, ip)) check_chain_key(current); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } - -EXPORT_SYMBOL_GPL(lock_set_subclass); +EXPORT_SYMBOL_GPL(lock_set_class); /* * We are not always called with irqs disabled - do that here, @@ -2943,7 +2947,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, current->lockdep_recursion = 0; raw_local_irq_restore(flags); } - EXPORT_SYMBOL_GPL(lock_acquire); void lock_release(struct lockdep_map *lock, int nested, @@ -2961,7 +2964,6 @@ void lock_release(struct lockdep_map *lock, int nested, current->lockdep_recursion = 0; raw_local_irq_restore(flags); } - EXPORT_SYMBOL_GPL(lock_release); #ifdef CONFIG_LOCK_STAT @@ -2999,7 +3001,7 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip) struct held_lock *hlock, *prev_hlock; struct lock_class_stats *stats; unsigned int depth; - int i, point; + int i, contention_point, contending_point; depth = curr->lockdep_depth; if (DEBUG_LOCKS_WARN_ON(!depth)) @@ -3023,18 +3025,22 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip) found_it: hlock->waittime_stamp = sched_clock(); - point = lock_contention_point(hlock_class(hlock), ip); + contention_point = lock_point(hlock_class(hlock)->contention_point, ip); + contending_point = lock_point(hlock_class(hlock)->contending_point, + lock->ip); stats = get_lock_stats(hlock_class(hlock)); - if (point < ARRAY_SIZE(stats->contention_point)) - stats->contention_point[point]++; + if (contention_point < LOCKSTAT_POINTS) + stats->contention_point[contention_point]++; + if (contending_point < LOCKSTAT_POINTS) + stats->contending_point[contending_point]++; if (lock->cpu != smp_processor_id()) stats->bounces[bounce_contended + !!hlock->read]++; put_lock_stats(stats); } static void -__lock_acquired(struct lockdep_map *lock) +__lock_acquired(struct lockdep_map *lock, unsigned long ip) { struct task_struct *curr = current; struct held_lock *hlock, *prev_hlock; @@ -3083,6 +3089,7 @@ found_it: put_lock_stats(stats); lock->cpu = cpu; + lock->ip = ip; } void lock_contended(struct lockdep_map *lock, unsigned long ip) @@ -3104,7 +3111,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) } EXPORT_SYMBOL_GPL(lock_contended); -void lock_acquired(struct lockdep_map *lock) +void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; @@ -3117,7 +3124,7 @@ void lock_acquired(struct lockdep_map *lock) raw_local_irq_save(flags); check_flags(flags); current->lockdep_recursion = 1; - __lock_acquired(lock); + __lock_acquired(lock, ip); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } @@ -3441,7 +3448,6 @@ retry: if (unlock) read_unlock(&tasklist_lock); } - EXPORT_SYMBOL_GPL(debug_show_all_locks); /* @@ -3462,7 +3468,6 @@ void debug_show_held_locks(struct task_struct *task) { __debug_show_held_locks(task); } - EXPORT_SYMBOL_GPL(debug_show_held_locks); void lockdep_sys_exit(void) diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c index 20dbcbf..13716b8 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/lockdep_proc.c @@ -470,11 +470,12 @@ static void seq_line(struct seq_file *m, char c, int offset, int length) static void snprint_time(char *buf, size_t bufsiz, s64 nr) { - unsigned long rem; + s64 div; + s32 rem; nr += 5; /* for display rounding */ - rem = do_div(nr, 1000); /* XXX: do_div_signed */ - snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10); + div = div_s64_rem(nr, 1000, &rem); + snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10); } static void seq_time(struct seq_file *m, s64 time) @@ -556,7 +557,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) if (stats->read_holdtime.nr) namelen += 2; - for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) { + for (i = 0; i < LOCKSTAT_POINTS; i++) { char sym[KSYM_SYMBOL_LEN]; char ip[32]; @@ -573,6 +574,23 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) stats->contention_point[i], ip, sym); } + for (i = 0; i < LOCKSTAT_POINTS; i++) { + char sym[KSYM_SYMBOL_LEN]; + char ip[32]; + + if (class->contending_point[i] == 0) + break; + + if (!i) + seq_line(m, '-', 40-namelen, namelen); + + sprint_symbol(sym, class->contending_point[i]); + snprintf(ip, sizeof(ip), "[<%p>]", + (void *)class->contending_point[i]); + seq_printf(m, "%40s %14lu %29s %s\n", name, + stats->contending_point[i], + ip, sym); + } if (i) { seq_puts(m, "\n"); seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1)); @@ -582,7 +600,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) static void seq_header(struct seq_file *m) { - seq_printf(m, "lock_stat version 0.2\n"); + seq_printf(m, "lock_stat version 0.3\n"); seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1)); seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s " "%14s %14s\n", diff --git a/kernel/marker.c b/kernel/marker.c index e9c6b2b..ea54f26 100644 --- a/kernel/marker.c +++ b/kernel/marker.c @@ -43,6 +43,7 @@ static DEFINE_MUTEX(markers_mutex); */ #define MARKER_HASH_BITS 6 #define MARKER_TABLE_SIZE (1 << MARKER_HASH_BITS) +static struct hlist_head marker_table[MARKER_TABLE_SIZE]; /* * Note about RCU : @@ -64,11 +65,10 @@ struct marker_entry { void *oldptr; int rcu_pending; unsigned char ptype:1; + unsigned char format_allocated:1; char name[0]; /* Contains name'\0'format'\0' */ }; -static struct hlist_head marker_table[MARKER_TABLE_SIZE]; - /** * __mark_empty_function - Empty probe callback * @probe_private: probe private data @@ -81,7 +81,7 @@ static struct hlist_head marker_table[MARKER_TABLE_SIZE]; * though the function pointer change and the marker enabling are two distinct * operations that modifies the execution flow of preemptible code. */ -void __mark_empty_function(void *probe_private, void *call_private, +notrace void __mark_empty_function(void *probe_private, void *call_private, const char *fmt, va_list *args) { } @@ -97,7 +97,8 @@ EXPORT_SYMBOL_GPL(__mark_empty_function); * need to put a full smp_rmb() in this branch. This is why we do not use * rcu_dereference() for the pointer read. */ -void marker_probe_cb(const struct marker *mdata, void *call_private, ...) +notrace void marker_probe_cb(const struct marker *mdata, + void *call_private, ...) { va_list args; char ptype; @@ -107,7 +108,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) * sure the teardown of the callbacks can be done correctly when they * are in modules and they insure RCU read coherency. */ - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); ptype = mdata->ptype; if (likely(!ptype)) { marker_probe_func *func; @@ -145,7 +146,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...) va_end(args); } } - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); } EXPORT_SYMBOL_GPL(marker_probe_cb); @@ -157,12 +158,13 @@ EXPORT_SYMBOL_GPL(marker_probe_cb); * * Should be connected to markers "MARK_NOARGS". */ -void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) +static notrace void marker_probe_cb_noarg(const struct marker *mdata, + void *call_private, ...) { va_list args; /* not initialized */ char ptype; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); ptype = mdata->ptype; if (likely(!ptype)) { marker_probe_func *func; @@ -195,9 +197,8 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) multi[i].func(multi[i].probe_private, call_private, mdata->format, &args); } - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); } -EXPORT_SYMBOL_GPL(marker_probe_cb_noarg); static void free_old_closure(struct rcu_head *head) { @@ -416,6 +417,7 @@ static struct marker_entry *add_marker(const char *name, const char *format) e->single.probe_private = NULL; e->multi = NULL; e->ptype = 0; + e->format_allocated = 0; e->refcount = 0; e->rcu_pending = 0; hlist_add_head(&e->hlist, head); @@ -447,6 +449,8 @@ static int remove_marker(const char *name) if (e->single.func != __mark_empty_function) return -EBUSY; hlist_del(&e->hlist); + if (e->format_allocated) + kfree(e->format); /* Make sure the call_rcu has been executed */ if (e->rcu_pending) rcu_barrier_sched(); @@ -457,57 +461,34 @@ static int remove_marker(const char *name) /* * Set the mark_entry format to the format found in the element. */ -static int marker_set_format(struct marker_entry **entry, const char *format) +static int marker_set_format(struct marker_entry *entry, const char *format) { - struct marker_entry *e; - size_t name_len = strlen((*entry)->name) + 1; - size_t format_len = strlen(format) + 1; - - - e = kmalloc(sizeof(struct marker_entry) + name_len + format_len, - GFP_KERNEL); - if (!e) + entry->format = kstrdup(format, GFP_KERNEL); + if (!entry->format) return -ENOMEM; - memcpy(&e->name[0], (*entry)->name, name_len); - e->format = &e->name[name_len]; - memcpy(e->format, format, format_len); - if (strcmp(e->format, MARK_NOARGS) == 0) - e->call = marker_probe_cb_noarg; - else - e->call = marker_probe_cb; - e->single = (*entry)->single; - e->multi = (*entry)->multi; - e->ptype = (*entry)->ptype; - e->refcount = (*entry)->refcount; - e->rcu_pending = 0; - hlist_add_before(&e->hlist, &(*entry)->hlist); - hlist_del(&(*entry)->hlist); - /* Make sure the call_rcu has been executed */ - if ((*entry)->rcu_pending) - rcu_barrier_sched(); - kfree(*entry); - *entry = e; + entry->format_allocated = 1; + trace_mark(core_marker_format, "name %s format %s", - e->name, e->format); + entry->name, entry->format); return 0; } /* * Sets the probe callback corresponding to one marker. */ -static int set_marker(struct marker_entry **entry, struct marker *elem, +static int set_marker(struct marker_entry *entry, struct marker *elem, int active) { - int ret; - WARN_ON(strcmp((*entry)->name, elem->name) != 0); + int ret = 0; + WARN_ON(strcmp(entry->name, elem->name) != 0); - if ((*entry)->format) { - if (strcmp((*entry)->format, elem->format) != 0) { + if (entry->format) { + if (strcmp(entry->format, elem->format) != 0) { printk(KERN_NOTICE "Format mismatch for probe %s " "(%s), marker (%s)\n", - (*entry)->name, - (*entry)->format, + entry->name, + entry->format, elem->format); return -EPERM; } @@ -523,37 +504,67 @@ static int set_marker(struct marker_entry **entry, struct marker *elem, * pass from a "safe" callback (with argument) to an "unsafe" * callback (does not set arguments). */ - elem->call = (*entry)->call; + elem->call = entry->call; /* * Sanity check : * We only update the single probe private data when the ptr is * set to a _non_ single probe! (0 -> 1 and N -> 1, N != 1) */ WARN_ON(elem->single.func != __mark_empty_function - && elem->single.probe_private - != (*entry)->single.probe_private && - !elem->ptype); - elem->single.probe_private = (*entry)->single.probe_private; + && elem->single.probe_private != entry->single.probe_private + && !elem->ptype); + elem->single.probe_private = entry->single.probe_private; /* * Make sure the private data is valid when we update the * single probe ptr. */ smp_wmb(); - elem->single.func = (*entry)->single.func; + elem->single.func = entry->single.func; /* * We also make sure that the new probe callbacks array is consistent * before setting a pointer to it. */ - rcu_assign_pointer(elem->multi, (*entry)->multi); + rcu_assign_pointer(elem->multi, entry->multi); /* * Update the function or multi probe array pointer before setting the * ptype. */ smp_wmb(); - elem->ptype = (*entry)->ptype; + elem->ptype = entry->ptype; + + if (elem->tp_name && (active ^ elem->state)) { + WARN_ON(!elem->tp_cb); + /* + * It is ok to directly call the probe registration because type + * checking has been done in the __trace_mark_tp() macro. + */ + + if (active) { + /* + * try_module_get should always succeed because we hold + * lock_module() to get the tp_cb address. + */ + ret = try_module_get(__module_text_address( + (unsigned long)elem->tp_cb)); + BUG_ON(!ret); + ret = tracepoint_probe_register_noupdate( + elem->tp_name, + elem->tp_cb); + } else { + ret = tracepoint_probe_unregister_noupdate( + elem->tp_name, + elem->tp_cb); + /* + * tracepoint_probe_update_all() must be called + * before the module containing tp_cb is unloaded. + */ + module_put(__module_text_address( + (unsigned long)elem->tp_cb)); + } + } elem->state = active; - return 0; + return ret; } /* @@ -564,7 +575,24 @@ static int set_marker(struct marker_entry **entry, struct marker *elem, */ static void disable_marker(struct marker *elem) { + int ret; + /* leave "call" as is. It is known statically. */ + if (elem->tp_name && elem->state) { + WARN_ON(!elem->tp_cb); + /* + * It is ok to directly call the probe registration because type + * checking has been done in the __trace_mark_tp() macro. + */ + ret = tracepoint_probe_unregister_noupdate(elem->tp_name, + elem->tp_cb); + WARN_ON(ret); + /* + * tracepoint_probe_update_all() must be called + * before the module containing tp_cb is unloaded. + */ + module_put(__module_text_address((unsigned long)elem->tp_cb)); + } elem->state = 0; elem->single.func = __mark_empty_function; /* Update the function before setting the ptype */ @@ -594,8 +622,7 @@ void marker_update_probe_range(struct marker *begin, for (iter = begin; iter < end; iter++) { mark_entry = get_marker(iter->name); if (mark_entry) { - set_marker(&mark_entry, iter, - !!mark_entry->refcount); + set_marker(mark_entry, iter, !!mark_entry->refcount); /* * ignore error, continue */ @@ -629,6 +656,7 @@ static void marker_update_probes(void) marker_update_probe_range(__start___markers, __stop___markers); /* Markers in modules. */ module_update_markers(); + tracepoint_probe_update_all(); } /** @@ -657,7 +685,7 @@ int marker_probe_register(const char *name, const char *format, ret = PTR_ERR(entry); } else if (format) { if (!entry->format) - ret = marker_set_format(&entry, format); + ret = marker_set_format(entry, format); else if (strcmp(entry->format, format)) ret = -EPERM; } @@ -676,10 +704,11 @@ int marker_probe_register(const char *name, const char *format, goto end; } mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker(name); - WARN_ON(!entry); + if (!entry) + goto end; if (entry->rcu_pending) rcu_barrier_sched(); entry->oldptr = old; @@ -720,7 +749,7 @@ int marker_probe_unregister(const char *name, rcu_barrier_sched(); old = marker_entry_remove_probe(entry, probe, probe_private); mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker(name); if (!entry) @@ -801,10 +830,11 @@ int marker_probe_unregister_private_data(marker_probe_func *probe, rcu_barrier_sched(); old = marker_entry_remove_probe(entry, NULL, probe_private); mutex_unlock(&markers_mutex); - marker_update_probes(); /* may update entry */ + marker_update_probes(); mutex_lock(&markers_mutex); entry = get_marker_from_private_data(probe, probe_private); - WARN_ON(!entry); + if (!entry) + goto end; if (entry->rcu_pending) rcu_barrier_sched(); entry->oldptr = old; @@ -848,8 +878,6 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe, if (!e->ptype) { if (num == 0 && e->single.func == probe) return e->single.probe_private; - else - break; } else { struct marker_probe_closure *closure; int match = 0; @@ -861,8 +889,42 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe, return closure[i].probe_private; } } + break; } } return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(marker_get_private_data); + +#ifdef CONFIG_MODULES + +int marker_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + switch (val) { + case MODULE_STATE_COMING: + marker_update_probe_range(mod->markers, + mod->markers + mod->num_markers); + break; + case MODULE_STATE_GOING: + marker_update_probe_range(mod->markers, + mod->markers + mod->num_markers); + break; + } + return 0; +} + +struct notifier_block marker_module_nb = { + .notifier_call = marker_module_notify, + .priority = 0, +}; + +static int init_markers(void) +{ + return register_module_notifier(&marker_module_nb); +} +__initcall(init_markers); + +#endif /* CONFIG_MODULES */ diff --git a/kernel/module.c b/kernel/module.c index 1f4cc00..c9332c9 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -43,7 +43,6 @@ #include <linux/device.h> #include <linux/string.h> #include <linux/mutex.h> -#include <linux/unwind.h> #include <linux/rculist.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -51,6 +50,7 @@ #include <asm/sections.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> +#include <linux/async.h> #if 0 #define DEBUGP printk @@ -757,8 +757,16 @@ sys_delete_module(const char __user *name_user, unsigned int flags) return -EFAULT; name[MODULE_NAME_LEN-1] = '\0'; - if (mutex_lock_interruptible(&module_mutex) != 0) - return -EINTR; + /* Create stop_machine threads since free_module relies on + * a non-failing stop_machine call. */ + ret = stop_machine_create(); + if (ret) + return ret; + + if (mutex_lock_interruptible(&module_mutex) != 0) { + ret = -EINTR; + goto out_stop; + } mod = find_module(name); if (!mod) { @@ -809,6 +817,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags) mod->exit(); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + async_synchronize_full(); mutex_lock(&module_mutex); /* Store the name of the last unloaded module for diagnostic purposes */ strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); @@ -817,10 +826,12 @@ sys_delete_module(const char __user *name_user, unsigned int flags) out: mutex_unlock(&module_mutex); +out_stop: + stop_machine_destroy(); return ret; } -static void print_unload_info(struct seq_file *m, struct module *mod) +static inline void print_unload_info(struct seq_file *m, struct module *mod) { struct module_use *use; int printed_something = 0; @@ -893,7 +904,7 @@ void module_put(struct module *module) EXPORT_SYMBOL(module_put); #else /* !CONFIG_MODULE_UNLOAD */ -static void print_unload_info(struct seq_file *m, struct module *mod) +static inline void print_unload_info(struct seq_file *m, struct module *mod) { /* We don't know the usage count, or what modules are using. */ seq_printf(m, " - -"); @@ -1439,8 +1450,6 @@ static void free_module(struct module *mod) remove_sect_attrs(mod); mod_kobject_remove(mod); - unwind_remove_table(mod->unwind_info, 0); - /* Arch-specific cleanup. */ module_arch_cleanup(mod); @@ -1578,11 +1587,21 @@ static int simplify_symbols(Elf_Shdr *sechdrs, return ret; } +/* Additional bytes needed by arch in front of individual sections */ +unsigned int __weak arch_mod_section_prepend(struct module *mod, + unsigned int section) +{ + /* default implementation just returns zero */ + return 0; +} + /* Update size with this section: return offset. */ -static long get_offset(unsigned int *size, Elf_Shdr *sechdr) +static long get_offset(struct module *mod, unsigned int *size, + Elf_Shdr *sechdr, unsigned int section) { long ret; + *size += arch_mod_section_prepend(mod, section); ret = ALIGN(*size, sechdr->sh_addralign ?: 1); *size = ret + sechdr->sh_size; return ret; @@ -1622,7 +1641,7 @@ static void layout_sections(struct module *mod, || strncmp(secstrings + s->sh_name, ".init", 5) == 0) continue; - s->sh_entsize = get_offset(&mod->core_size, s); + s->sh_entsize = get_offset(mod, &mod->core_size, s, i); DEBUGP("\t%s\n", secstrings + s->sh_name); } if (m == 0) @@ -1640,7 +1659,7 @@ static void layout_sections(struct module *mod, || strncmp(secstrings + s->sh_name, ".init", 5) != 0) continue; - s->sh_entsize = (get_offset(&mod->init_size, s) + s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) | INIT_OFFSET_MASK); DEBUGP("\t%s\n", secstrings + s->sh_name); } @@ -1725,15 +1744,15 @@ static const struct kernel_symbol *lookup_symbol(const char *name, return NULL; } -static int is_exported(const char *name, const struct module *mod) +static int is_exported(const char *name, unsigned long value, + const struct module *mod) { - if (!mod && lookup_symbol(name, __start___ksymtab, __stop___ksymtab)) - return 1; + const struct kernel_symbol *ks; + if (!mod) + ks = lookup_symbol(name, __start___ksymtab, __stop___ksymtab); else - if (mod && lookup_symbol(name, mod->syms, mod->syms + mod->num_syms)) - return 1; - else - return 0; + ks = lookup_symbol(name, mod->syms, mod->syms + mod->num_syms); + return ks != NULL && ks->value == value; } /* As per nm */ @@ -1847,7 +1866,6 @@ static noinline struct module *load_module(void __user *umod, unsigned int symindex = 0; unsigned int strindex = 0; unsigned int modindex, versindex, infoindex, pcpuindex; - unsigned int unwindex = 0; unsigned int num_kp, num_mcount; struct kernel_param *kp; struct module *mod; @@ -1865,6 +1883,13 @@ static noinline struct module *load_module(void __user *umod, /* vmalloc barfs on "unusual" numbers. Check here */ if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL) return ERR_PTR(-ENOMEM); + + /* Create stop_machine threads since the error path relies on + * a non-failing stop_machine call. */ + err = stop_machine_create(); + if (err) + goto free_hdr; + if (copy_from_user(hdr, umod, len) != 0) { err = -EFAULT; goto free_hdr; @@ -1930,9 +1955,6 @@ static noinline struct module *load_module(void __user *umod, versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); -#ifdef ARCH_UNWIND_SECTION_NAME - unwindex = find_sec(hdr, sechdrs, secstrings, ARCH_UNWIND_SECTION_NAME); -#endif /* Don't keep modinfo and version sections. */ sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC; @@ -1942,8 +1964,6 @@ static noinline struct module *load_module(void __user *umod, sechdrs[symindex].sh_flags |= SHF_ALLOC; sechdrs[strindex].sh_flags |= SHF_ALLOC; #endif - if (unwindex) - sechdrs[unwindex].sh_flags |= SHF_ALLOC; /* Check module struct version now, before we try to use module. */ if (!check_modstruct_version(sechdrs, versindex, mod)) { @@ -2184,24 +2204,15 @@ static noinline struct module *load_module(void __user *umod, struct mod_debug *debug; unsigned int num_debug; -#ifdef CONFIG_MARKERS - marker_update_probe_range(mod->markers, - mod->markers + mod->num_markers); -#endif debug = section_objs(hdr, sechdrs, secstrings, "__verbose", sizeof(*debug), &num_debug); dynamic_printk_setup(debug, num_debug); - -#ifdef CONFIG_TRACEPOINTS - tracepoint_update_probe_range(mod->tracepoints, - mod->tracepoints + mod->num_tracepoints); -#endif } /* sechdrs[0].sh_size is always zero */ mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc", sizeof(*mseg), &num_mcount); - ftrace_init_module(mseg, mseg + num_mcount); + ftrace_init_module(mod, mseg, mseg + num_mcount); err = module_finalize(hdr, sechdrs, mod); if (err < 0) @@ -2249,14 +2260,10 @@ static noinline struct module *load_module(void __user *umod, add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs); - /* Size of section 0 is 0, so this works well if no unwind info. */ - mod->unwind_info = unwind_add_table(mod, - (void *)sechdrs[unwindex].sh_addr, - sechdrs[unwindex].sh_size); - /* Get rid of temporary copy */ vfree(hdr); + stop_machine_destroy(); /* Done! */ return mod; @@ -2279,6 +2286,7 @@ static noinline struct module *load_module(void __user *umod, kfree(args); free_hdr: vfree(hdr); + stop_machine_destroy(); return ERR_PTR(err); truncated: @@ -2346,11 +2354,12 @@ sys_init_module(void __user *umod, /* Now it's a first class citizen! Wake up anyone waiting for it. */ mod->state = MODULE_STATE_LIVE; wake_up(&module_wq); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_LIVE, mod); mutex_lock(&module_mutex); /* Drop initial reference. */ module_put(mod); - unwind_remove_table(mod->unwind_info, 1); module_free(mod, mod->module_init); mod->module_init = NULL; mod->init_size = 0; @@ -2385,7 +2394,7 @@ static const char *get_ksymbol(struct module *mod, unsigned long nextval; /* At worse, next value is at end of module */ - if (within(addr, mod->module_init, mod->init_size)) + if (within_module_init(addr, mod)) nextval = (unsigned long)mod->module_init+mod->init_text_size; else nextval = (unsigned long)mod->module_core+mod->core_text_size; @@ -2433,8 +2442,8 @@ const char *module_address_lookup(unsigned long addr, preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { - if (within(addr, mod->module_init, mod->init_size) - || within(addr, mod->module_core, mod->core_size)) { + if (within_module_init(addr, mod) || + within_module_core(addr, mod)) { if (modname) *modname = mod->name; ret = get_ksymbol(mod, addr, size, offset); @@ -2456,8 +2465,8 @@ int lookup_module_symbol_name(unsigned long addr, char *symname) preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { - if (within(addr, mod->module_init, mod->init_size) || - within(addr, mod->module_core, mod->core_size)) { + if (within_module_init(addr, mod) || + within_module_core(addr, mod)) { const char *sym; sym = get_ksymbol(mod, addr, NULL, NULL); @@ -2480,8 +2489,8 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { - if (within(addr, mod->module_init, mod->init_size) || - within(addr, mod->module_core, mod->core_size)) { + if (within_module_init(addr, mod) || + within_module_core(addr, mod)) { const char *sym; sym = get_ksymbol(mod, addr, size, offset); @@ -2513,7 +2522,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, strlcpy(name, mod->strtab + mod->symtab[symnum].st_name, KSYM_NAME_LEN); strlcpy(module_name, mod->name, MODULE_NAME_LEN); - *exported = is_exported(name, mod); + *exported = is_exported(name, *value, mod); preempt_enable(); return 0; } @@ -2700,7 +2709,7 @@ int is_module_address(unsigned long addr) preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { - if (within(addr, mod->module_core, mod->core_size)) { + if (within_module_core(addr, mod)) { preempt_enable(); return 1; } @@ -2713,7 +2722,7 @@ int is_module_address(unsigned long addr) /* Is this a valid kernel address? */ -struct module *__module_text_address(unsigned long addr) +__notrace_funcgraph struct module *__module_text_address(unsigned long addr) { struct module *mod; diff --git a/kernel/mutex.c b/kernel/mutex.c index 12c779d..4f45d4b 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -59,7 +59,7 @@ EXPORT_SYMBOL(__mutex_init); * We also put the fastpath first in the kernel image, to make sure the * branch is predicted by the CPU as default-untaken. */ -static void noinline __sched +static __used noinline void __sched __mutex_lock_slowpath(atomic_t *lock_count); /*** @@ -96,7 +96,7 @@ void inline __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif -static noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count); +static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count); /*** * mutex_unlock - release the mutex @@ -184,7 +184,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } done: - lock_acquired(&lock->dep_map); + lock_acquired(&lock->dep_map, ip); /* got the lock - rejoice! */ mutex_remove_waiter(lock, &waiter, task_thread_info(task)); debug_mutex_set_owner(lock, task_thread_info(task)); @@ -268,7 +268,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested) /* * Release the lock, slowpath: */ -static noinline void +static __used noinline void __mutex_unlock_slowpath(atomic_t *lock_count) { __mutex_unlock_common_slowpath(lock_count, 1); @@ -313,7 +313,7 @@ int __sched mutex_lock_killable(struct mutex *lock) } EXPORT_SYMBOL(mutex_lock_killable); -static noinline void __sched +static __used noinline void __sched __mutex_lock_slowpath(atomic_t *lock_count) { struct mutex *lock = container_of(lock_count, struct mutex, count); diff --git a/kernel/notifier.c b/kernel/notifier.c index 4282c0a..61d5aa5 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -82,6 +82,14 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl, while (nb && nr_to_call) { next_nb = rcu_dereference(nb->next); + +#ifdef CONFIG_DEBUG_NOTIFIERS + if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) { + WARN(1, "Invalid notifier called!"); + nb = next_nb; + continue; + } +#endif ret = nb->notifier_call(nb, val, v); if (nr_calls) diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c index 43c2111..78bc3fd 100644 --- a/kernel/ns_cgroup.c +++ b/kernel/ns_cgroup.c @@ -13,7 +13,6 @@ struct ns_cgroup { struct cgroup_subsys_state css; - spinlock_t lock; }; struct cgroup_subsys ns_subsys; @@ -84,7 +83,6 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss, ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL); if (!ns_cgroup) return ERR_PTR(-ENOMEM); - spin_lock_init(&ns_cgroup->lock); return &ns_cgroup->css; } diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 1d3ef29..63598dc 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -80,12 +80,6 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_pid; } - new_nsp->user_ns = copy_user_ns(flags, tsk->nsproxy->user_ns); - if (IS_ERR(new_nsp->user_ns)) { - err = PTR_ERR(new_nsp->user_ns); - goto out_user; - } - new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns); if (IS_ERR(new_nsp->net_ns)) { err = PTR_ERR(new_nsp->net_ns); @@ -95,9 +89,6 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, return new_nsp; out_net: - if (new_nsp->user_ns) - put_user_ns(new_nsp->user_ns); -out_user: if (new_nsp->pid_ns) put_pid_ns(new_nsp->pid_ns); out_pid: @@ -130,7 +121,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) get_nsproxy(old_ns); if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWUSER | CLONE_NEWPID | CLONE_NEWNET))) + CLONE_NEWPID | CLONE_NEWNET))) return 0; if (!capable(CAP_SYS_ADMIN)) { @@ -173,8 +164,6 @@ void free_nsproxy(struct nsproxy *ns) put_ipc_ns(ns->ipc_ns); if (ns->pid_ns) put_pid_ns(ns->pid_ns); - if (ns->user_ns) - put_user_ns(ns->user_ns); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); } @@ -189,7 +178,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, int err = 0; if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWUSER | CLONE_NEWNET))) + CLONE_NEWNET))) return 0; if (!capable(CAP_SYS_ADMIN)) diff --git a/kernel/panic.c b/kernel/panic.c index 4d50883..2a2ff36 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -21,6 +21,7 @@ #include <linux/debug_locks.h> #include <linux/random.h> #include <linux/kallsyms.h> +#include <linux/dmi.h> int panic_on_oops; static unsigned long tainted_mask; @@ -298,6 +299,8 @@ static int init_oops_id(void) { if (!oops_id) get_random_bytes(&oops_id, sizeof(oops_id)); + else + oops_id++; return 0; } @@ -321,36 +324,27 @@ void oops_exit(void) } #ifdef WANT_WARN_ON_SLOWPATH -void warn_on_slowpath(const char *file, int line) -{ - char function[KSYM_SYMBOL_LEN]; - unsigned long caller = (unsigned long) __builtin_return_address(0); - sprint_symbol(function, caller); - - printk(KERN_WARNING "------------[ cut here ]------------\n"); - printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file, - line, function); - print_modules(); - dump_stack(); - print_oops_end_marker(); - add_taint(TAINT_WARN); -} -EXPORT_SYMBOL(warn_on_slowpath); - - void warn_slowpath(const char *file, int line, const char *fmt, ...) { va_list args; char function[KSYM_SYMBOL_LEN]; unsigned long caller = (unsigned long)__builtin_return_address(0); + const char *board; + sprint_symbol(function, caller); printk(KERN_WARNING "------------[ cut here ]------------\n"); printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file, line, function); - va_start(args, fmt); - vprintk(fmt, args); - va_end(args); + board = dmi_get_system_info(DMI_PRODUCT_NAME); + if (board) + printk(KERN_WARNING "Hardware name: %s\n", board); + + if (fmt) { + va_start(args, fmt); + vprintk(fmt, args); + va_end(args); + } print_modules(); dump_stack(); diff --git a/kernel/pid.c b/kernel/pid.c index 064e76a..1b3586f 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -474,8 +474,14 @@ pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) } EXPORT_SYMBOL(task_session_nr_ns); +struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) +{ + return ns_of_pid(task_pid(tsk)); +} +EXPORT_SYMBOL_GPL(task_active_pid_ns); + /* - * Used by proc to find the first pid that is greater then or equal to nr. + * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 4e5288a..157de3a 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -58,21 +58,21 @@ void thread_group_cputime( struct task_struct *tsk, struct task_cputime *times) { - struct signal_struct *sig; + struct task_cputime *totals, *tot; int i; - struct task_cputime *tot; - sig = tsk->signal; - if (unlikely(!sig) || !sig->cputime.totals) { + totals = tsk->signal->cputime.totals; + if (!totals) { times->utime = tsk->utime; times->stime = tsk->stime; times->sum_exec_runtime = tsk->se.sum_exec_runtime; return; } + times->stime = times->utime = cputime_zero; times->sum_exec_runtime = 0; for_each_possible_cpu(i) { - tot = per_cpu_ptr(tsk->signal->cputime.totals, i); + tot = per_cpu_ptr(totals, i); times->utime = cputime_add(times->utime, tot->utime); times->stime = cputime_add(times->stime, tot->stime); times->sum_exec_runtime += tot->sum_exec_runtime; diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index a140e44..887c637 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -116,7 +116,7 @@ static DEFINE_SPINLOCK(idr_lock); * must supply functions here, even if the function just returns * ENOSYS. The standard POSIX timer management code assumes the * following: 1.) The k_itimer struct (sched.h) is used for the - * timer. 2.) The list, it_lock, it_clock, it_id and it_process + * timer. 2.) The list, it_lock, it_clock, it_id and it_pid * fields are not modified by timer code. * * At this time all functions EXCEPT clock_nanosleep can be @@ -319,7 +319,8 @@ void do_schedule_next_timer(struct siginfo *info) int posix_timer_event(struct k_itimer *timr, int si_private) { - int shared, ret; + struct task_struct *task; + int shared, ret = -1; /* * FIXME: if ->sigq is queued we can race with * dequeue_signal()->do_schedule_next_timer(). @@ -333,8 +334,13 @@ int posix_timer_event(struct k_itimer *timr, int si_private) */ timr->sigq->info.si_sys_private = si_private; - shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID); - ret = send_sigqueue(timr->sigq, timr->it_process, shared); + rcu_read_lock(); + task = pid_task(timr->it_pid, PIDTYPE_PID); + if (task) { + shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID); + ret = send_sigqueue(timr->sigq, task, shared); + } + rcu_read_unlock(); /* If we failed to send the signal the timer stops. */ return ret > 0; } @@ -411,7 +417,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) return ret; } -static struct task_struct * good_sigevent(sigevent_t * event) +static struct pid *good_sigevent(sigevent_t * event) { struct task_struct *rtn = current->group_leader; @@ -425,7 +431,7 @@ static struct task_struct * good_sigevent(sigevent_t * event) ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX))) return NULL; - return rtn; + return task_pid(rtn); } void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock) @@ -464,6 +470,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set) idr_remove(&posix_timers_id, tmr->it_id); spin_unlock_irqrestore(&idr_lock, flags); } + put_pid(tmr->it_pid); sigqueue_free(tmr->sigq); kmem_cache_free(posix_timers_cache, tmr); } @@ -477,7 +484,6 @@ sys_timer_create(const clockid_t which_clock, { struct k_itimer *new_timer; int error, new_timer_id; - struct task_struct *process; sigevent_t event; int it_id_set = IT_ID_NOT_SET; @@ -531,11 +537,9 @@ sys_timer_create(const clockid_t which_clock, goto out; } rcu_read_lock(); - process = good_sigevent(&event); - if (process) - get_task_struct(process); + new_timer->it_pid = get_pid(good_sigevent(&event)); rcu_read_unlock(); - if (!process) { + if (!new_timer->it_pid) { error = -EINVAL; goto out; } @@ -543,8 +547,7 @@ sys_timer_create(const clockid_t which_clock, event.sigev_notify = SIGEV_SIGNAL; event.sigev_signo = SIGALRM; event.sigev_value.sival_int = new_timer->it_id; - process = current->group_leader; - get_task_struct(process); + new_timer->it_pid = get_pid(task_tgid(current)); } new_timer->it_sigev_notify = event.sigev_notify; @@ -554,7 +557,7 @@ sys_timer_create(const clockid_t which_clock, new_timer->sigq->info.si_code = SI_TIMER; spin_lock_irq(¤t->sighand->siglock); - new_timer->it_process = process; + new_timer->it_signal = current->signal; list_add(&new_timer->list, ¤t->signal->posix_timers); spin_unlock_irq(¤t->sighand->siglock); @@ -589,8 +592,7 @@ static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags) timr = idr_find(&posix_timers_id, (int)timer_id); if (timr) { spin_lock(&timr->it_lock); - if (timr->it_process && - same_thread_group(timr->it_process, current)) { + if (timr->it_signal == current->signal) { spin_unlock(&idr_lock); return timr; } @@ -837,8 +839,7 @@ retry_delete: * This keeps any tasks waiting on the spin lock from thinking * they got something (see the lock code above). */ - put_task_struct(timer->it_process); - timer->it_process = NULL; + timer->it_signal = NULL; unlock_timer(timer, flags); release_posix_timer(timer, IT_ID_SET); @@ -864,8 +865,7 @@ retry_delete: * This keeps any tasks waiting on the spin lock from thinking * they got something (see the lock code above). */ - put_task_struct(timer->it_process); - timer->it_process = NULL; + timer->it_signal = NULL; unlock_timer(timer, flags); release_posix_timer(timer, IT_ID_SET); diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 096fe48..45e8541 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -22,7 +22,6 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> -#include <linux/ftrace.h> #include "power.h" @@ -257,7 +256,7 @@ static int create_image(int platform_mode) int hibernation_snapshot(int platform_mode) { - int error, ftrace_save; + int error; error = platform_begin(platform_mode); if (error) @@ -269,7 +268,6 @@ int hibernation_snapshot(int platform_mode) goto Close; suspend_console(); - ftrace_save = __ftrace_enabled_save(); error = device_suspend(PMSG_FREEZE); if (error) goto Recover_platform; @@ -299,7 +297,6 @@ int hibernation_snapshot(int platform_mode) Resume_devices: device_resume(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); - __ftrace_enabled_restore(ftrace_save); resume_console(); Close: platform_end(platform_mode); @@ -370,11 +367,10 @@ static int resume_target_kernel(void) int hibernation_restore(int platform_mode) { - int error, ftrace_save; + int error; pm_prepare_console(); suspend_console(); - ftrace_save = __ftrace_enabled_save(); error = device_suspend(PMSG_QUIESCE); if (error) goto Finish; @@ -389,7 +385,6 @@ int hibernation_restore(int platform_mode) platform_restore_cleanup(platform_mode); device_resume(PMSG_RECOVER); Finish: - __ftrace_enabled_restore(ftrace_save); resume_console(); pm_restore_console(); return error; @@ -402,7 +397,7 @@ int hibernation_restore(int platform_mode) int hibernation_platform_enter(void) { - int error, ftrace_save; + int error; if (!hibernation_ops) return -ENOSYS; @@ -417,7 +412,6 @@ int hibernation_platform_enter(void) goto Close; suspend_console(); - ftrace_save = __ftrace_enabled_save(); error = device_suspend(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -452,7 +446,6 @@ int hibernation_platform_enter(void) hibernation_ops->finish(); Resume_devices: device_resume(PMSG_RESTORE); - __ftrace_enabled_restore(ftrace_save); resume_console(); Close: hibernation_ops->end(); diff --git a/kernel/power/main.c b/kernel/power/main.c index b8f7ce9..2399888 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -22,7 +22,6 @@ #include <linux/freezer.h> #include <linux/vmstat.h> #include <linux/syscalls.h> -#include <linux/ftrace.h> #include "power.h" @@ -317,7 +316,7 @@ static int suspend_enter(suspend_state_t state) */ int suspend_devices_and_enter(suspend_state_t state) { - int error, ftrace_save; + int error; if (!suspend_ops) return -ENOSYS; @@ -328,7 +327,6 @@ int suspend_devices_and_enter(suspend_state_t state) goto Close; } suspend_console(); - ftrace_save = __ftrace_enabled_save(); suspend_test_start(); error = device_suspend(PMSG_SUSPEND); if (error) { @@ -360,7 +358,6 @@ int suspend_devices_and_enter(suspend_state_t state) suspend_test_start(); device_resume(PMSG_RESUME); suspend_test_finish("resume devices"); - __ftrace_enabled_restore(ftrace_save); resume_console(); Close: if (suspend_ops->end) @@ -618,7 +615,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) /* this may fail if the RTC hasn't been initialized */ status = rtc_read_time(rtc, &alm.time); if (status < 0) { - printk(err_readtime, rtc->dev.bus_id, status); + printk(err_readtime, dev_name(&rtc->dev), status); return; } rtc_tm_to_time(&alm.time, &now); @@ -629,7 +626,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) status = rtc_set_alarm(rtc, &alm); if (status < 0) { - printk(err_wakealarm, rtc->dev.bus_id, status); + printk(err_wakealarm, dev_name(&rtc->dev), status); return; } @@ -663,7 +660,7 @@ static int __init has_wakealarm(struct device *dev, void *name_ptr) if (!device_may_wakeup(candidate->dev.parent)) return 0; - *(char **)name_ptr = dev->bus_id; + *(const char **)name_ptr = dev_name(dev); return 1; } diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c index 72016f0..9789083 100644 --- a/kernel/power/poweroff.c +++ b/kernel/power/poweroff.c @@ -27,7 +27,7 @@ static DECLARE_WORK(poweroff_work, do_poweroff); static void handle_poweroff(int key, struct tty_struct *tty) { /* run sysrq poweroff on boot cpu */ - schedule_work_on(first_cpu(cpu_online_map), &poweroff_work); + schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work); } static struct sysrq_key_op sysrq_poweroff_op = { diff --git a/kernel/printk.c b/kernel/printk.c index f492f15..7015733 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -619,7 +619,7 @@ static int acquire_console_semaphore_for_printk(unsigned int cpu) static const char recursion_bug_msg [] = KERN_CRIT "BUG: recent printk recursion!\n"; static int recursion_bug; - static int new_text_line = 1; +static int new_text_line = 1; static char printk_buf[1024]; asmlinkage int vprintk(const char *fmt, va_list args) @@ -662,7 +662,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) if (recursion_bug) { recursion_bug = 0; strcpy(printk_buf, recursion_bug_msg); - printed_len = sizeof(recursion_bug_msg); + printed_len = strlen(recursion_bug_msg); } /* Emit the output into the temporary buffer */ printed_len += vscnprintf(printk_buf + printed_len, diff --git a/kernel/profile.c b/kernel/profile.c index dc41827..784933a 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -45,7 +45,7 @@ static unsigned long prof_len, prof_shift; int prof_on __read_mostly; EXPORT_SYMBOL_GPL(prof_on); -static cpumask_t prof_cpu_mask = CPU_MASK_ALL; +static cpumask_var_t prof_cpu_mask; #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits); static DEFINE_PER_CPU(int, cpu_profile_flip); @@ -113,9 +113,13 @@ int __ref profile_init(void) buffer_bytes = prof_len*sizeof(atomic_t); if (!slab_is_available()) { prof_buffer = alloc_bootmem(buffer_bytes); + alloc_bootmem_cpumask_var(&prof_cpu_mask); return 0; } + if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL)) + return -ENOMEM; + prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL); if (prof_buffer) return 0; @@ -128,6 +132,7 @@ int __ref profile_init(void) if (prof_buffer) return 0; + free_cpumask_var(prof_cpu_mask); return -ENOMEM; } @@ -386,13 +391,15 @@ out_free: return NOTIFY_BAD; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - cpu_set(cpu, prof_cpu_mask); + if (prof_cpu_mask != NULL) + cpumask_set_cpu(cpu, prof_cpu_mask); break; case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: - cpu_clear(cpu, prof_cpu_mask); + if (prof_cpu_mask != NULL) + cpumask_clear_cpu(cpu, prof_cpu_mask); if (per_cpu(cpu_profile_hits, cpu)[0]) { page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]); per_cpu(cpu_profile_hits, cpu)[0] = NULL; @@ -430,19 +437,19 @@ void profile_tick(int type) if (type == CPU_PROFILING && timer_hook) timer_hook(regs); - if (!user_mode(regs) && cpu_isset(smp_processor_id(), prof_cpu_mask)) + if (!user_mode(regs) && prof_cpu_mask != NULL && + cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) profile_hit(type, (void *)profile_pc(regs)); } #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <asm/uaccess.h> -#include <asm/ptrace.h> static int prof_cpu_mask_read_proc(char *page, char **start, off_t off, int count, int *eof, void *data) { - int len = cpumask_scnprintf(page, count, *(cpumask_t *)data); + int len = cpumask_scnprintf(page, count, data); if (count - len < 2) return -EINVAL; len += sprintf(page + len, "\n"); @@ -452,16 +459,20 @@ static int prof_cpu_mask_read_proc(char *page, char **start, off_t off, static int prof_cpu_mask_write_proc(struct file *file, const char __user *buffer, unsigned long count, void *data) { - cpumask_t *mask = (cpumask_t *)data; + struct cpumask *mask = data; unsigned long full_count = count, err; - cpumask_t new_value; + cpumask_var_t new_value; - err = cpumask_parse_user(buffer, count, new_value); - if (err) - return err; + if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) + return -ENOMEM; - *mask = new_value; - return full_count; + err = cpumask_parse_user(buffer, count, new_value); + if (!err) { + cpumask_copy(mask, new_value); + err = full_count; + } + free_cpumask_var(new_value); + return err; } void create_prof_cpu_mask(struct proc_dir_entry *root_irq_dir) @@ -472,7 +483,7 @@ void create_prof_cpu_mask(struct proc_dir_entry *root_irq_dir) entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir); if (!entry) return; - entry->data = (void *)&prof_cpu_mask; + entry->data = prof_cpu_mask; entry->read_proc = prof_cpu_mask_read_proc; entry->write_proc = prof_cpu_mask_write_proc; } @@ -544,7 +555,7 @@ static const struct file_operations proc_profile_operations = { }; #ifdef CONFIG_SMP -static inline void profile_nop(void *unused) +static void profile_nop(void *unused) { } diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 4c8bcd7..29dc700 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -25,6 +25,17 @@ #include <asm/pgtable.h> #include <asm/uaccess.h> + +/* + * Initialize a new task whose father had been ptraced. + * + * Called from copy_process(). + */ +void ptrace_fork(struct task_struct *child, unsigned long clone_flags) +{ + arch_ptrace_fork(child, clone_flags); +} + /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. @@ -72,6 +83,7 @@ void __ptrace_unlink(struct task_struct *child) child->parent = child->real_parent; list_del_init(&child->ptrace_entry); + arch_ptrace_untrace(child); if (task_is_traced(child)) ptrace_untrace(child); } @@ -115,6 +127,8 @@ int ptrace_check_attach(struct task_struct *child, int kill) int __ptrace_may_access(struct task_struct *task, unsigned int mode) { + const struct cred *cred = current_cred(), *tcred; + /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. @@ -127,13 +141,19 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) /* Don't let security modules deny introspection */ if (task == current) return 0; - if (((current->uid != task->euid) || - (current->uid != task->suid) || - (current->uid != task->uid) || - (current->gid != task->egid) || - (current->gid != task->sgid) || - (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE)) + rcu_read_lock(); + tcred = __task_cred(task); + if ((cred->uid != tcred->euid || + cred->uid != tcred->suid || + cred->uid != tcred->uid || + cred->gid != tcred->egid || + cred->gid != tcred->sgid || + cred->gid != tcred->gid) && + !capable(CAP_SYS_PTRACE)) { + rcu_read_unlock(); return -EPERM; + } + rcu_read_unlock(); smp_rmb(); if (task->mm) dumpable = get_dumpable(task->mm); @@ -163,6 +183,14 @@ int ptrace_attach(struct task_struct *task) if (same_thread_group(task, current)) goto out; + /* Protect exec's credential calculations against our interference; + * SUID, SGID and LSM creds get determined differently under ptrace. + */ + retval = mutex_lock_interruptible(¤t->cred_exec_mutex); + if (retval < 0) + goto out; + + retval = -EPERM; repeat: /* * Nasty, nasty. @@ -202,6 +230,7 @@ repeat: bad: write_unlock_irqrestore(&tasklist_lock, flags); task_unlock(task); + mutex_unlock(¤t->cred_exec_mutex); out: return retval; } diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index 37f72e551..490934f 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -63,14 +63,14 @@ static struct rcu_ctrlblk rcu_ctrlblk = { .completed = -300, .pending = -300, .lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock), - .cpumask = CPU_MASK_NONE, + .cpumask = CPU_BITS_NONE, }; static struct rcu_ctrlblk rcu_bh_ctrlblk = { .cur = -300, .completed = -300, .pending = -300, .lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock), - .cpumask = CPU_MASK_NONE, + .cpumask = CPU_BITS_NONE, }; DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L }; @@ -85,7 +85,6 @@ static void force_quiescent_state(struct rcu_data *rdp, struct rcu_ctrlblk *rcp) { int cpu; - cpumask_t cpumask; unsigned long flags; set_need_resched(); @@ -96,10 +95,10 @@ static void force_quiescent_state(struct rcu_data *rdp, * Don't send IPI to itself. With irqs disabled, * rdp->cpu is the current cpu. * - * cpu_online_map is updated by the _cpu_down() + * cpu_online_mask is updated by the _cpu_down() * using __stop_machine(). Since we're in irqs disabled * section, __stop_machine() is not exectuting, hence - * the cpu_online_map is stable. + * the cpu_online_mask is stable. * * However, a cpu might have been offlined _just_ before * we disabled irqs while entering here. @@ -107,13 +106,14 @@ static void force_quiescent_state(struct rcu_data *rdp, * notification, leading to the offlined cpu's bit * being set in the rcp->cpumask. * - * Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent + * Hence cpumask = (rcp->cpumask & cpu_online_mask) to prevent * sending smp_reschedule() to an offlined CPU. */ - cpus_and(cpumask, rcp->cpumask, cpu_online_map); - cpu_clear(rdp->cpu, cpumask); - for_each_cpu_mask_nr(cpu, cpumask) - smp_send_reschedule(cpu); + for_each_cpu_and(cpu, + to_cpumask(rcp->cpumask), cpu_online_mask) { + if (cpu != rdp->cpu) + smp_send_reschedule(cpu); + } } spin_unlock_irqrestore(&rcp->lock, flags); } @@ -191,9 +191,9 @@ static void print_other_cpu_stall(struct rcu_ctrlblk *rcp) /* OK, time to rat on our buddy... */ - printk(KERN_ERR "RCU detected CPU stalls:"); + printk(KERN_ERR "INFO: RCU detected CPU stalls:"); for_each_possible_cpu(cpu) { - if (cpu_isset(cpu, rcp->cpumask)) + if (cpumask_test_cpu(cpu, to_cpumask(rcp->cpumask))) printk(" %d", cpu); } printk(" (detected by %d, t=%ld jiffies)\n", @@ -204,7 +204,7 @@ static void print_cpu_stall(struct rcu_ctrlblk *rcp) { unsigned long flags; - printk(KERN_ERR "RCU detected CPU %d stall (t=%lu/%lu jiffies)\n", + printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu/%lu jiffies)\n", smp_processor_id(), jiffies, jiffies - rcp->gp_start); dump_stack(); @@ -221,7 +221,8 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp) long delta; delta = jiffies - rcp->jiffies_stall; - if (cpu_isset(smp_processor_id(), rcp->cpumask) && delta >= 0) { + if (cpumask_test_cpu(smp_processor_id(), to_cpumask(rcp->cpumask)) && + delta >= 0) { /* We haven't checked in, so go dump stack. */ print_cpu_stall(rcp); @@ -393,7 +394,8 @@ static void rcu_start_batch(struct rcu_ctrlblk *rcp) * unnecessarily. */ smp_mb(); - cpus_andnot(rcp->cpumask, cpu_online_map, nohz_cpu_mask); + cpumask_andnot(to_cpumask(rcp->cpumask), + cpu_online_mask, nohz_cpu_mask); rcp->signaled = 0; } @@ -406,8 +408,8 @@ static void rcu_start_batch(struct rcu_ctrlblk *rcp) */ static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp) { - cpu_clear(cpu, rcp->cpumask); - if (cpus_empty(rcp->cpumask)) { + cpumask_clear_cpu(cpu, to_cpumask(rcp->cpumask)); + if (cpumask_empty(to_cpumask(rcp->cpumask))) { /* batch completed ! */ rcp->completed = rcp->cur; rcu_start_batch(rcp); diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index ad63af8..d92a76a 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -77,8 +77,15 @@ void wakeme_after_rcu(struct rcu_head *head) * sections are delimited by rcu_read_lock() and rcu_read_unlock(), * and may be nested. */ -void synchronize_rcu(void); /* Makes kernel-doc tools happy */ -synchronize_rcu_xxx(synchronize_rcu, call_rcu) +void synchronize_rcu(void) +{ + struct rcu_synchronize rcu; + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} EXPORT_SYMBOL_GPL(synchronize_rcu); static void rcu_barrier_callback(struct rcu_head *notused) diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c index 59236e8..33cfc50 100644 --- a/kernel/rcupreempt.c +++ b/kernel/rcupreempt.c @@ -164,7 +164,8 @@ static char *rcu_try_flip_state_names[] = { "idle", "waitack", "waitzero", "waitmb" }; #endif /* #ifdef CONFIG_RCU_TRACE */ -static cpumask_t rcu_cpu_online_map __read_mostly = CPU_MASK_NONE; +static DECLARE_BITMAP(rcu_cpu_online_map, NR_CPUS) __read_mostly + = CPU_BITS_NONE; /* * Enum and per-CPU flag to determine when each CPU has seen @@ -551,6 +552,16 @@ void rcu_irq_exit(void) } } +void rcu_nmi_enter(void) +{ + rcu_irq_enter(); +} + +void rcu_nmi_exit(void) +{ + rcu_irq_exit(); +} + static void dyntick_save_progress_counter(int cpu) { struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); @@ -748,7 +759,7 @@ rcu_try_flip_idle(void) /* Now ask each CPU for acknowledgement of the flip. */ - for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) { + for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) { per_cpu(rcu_flip_flag, cpu) = rcu_flipped; dyntick_save_progress_counter(cpu); } @@ -766,7 +777,7 @@ rcu_try_flip_waitack(void) int cpu; RCU_TRACE_ME(rcupreempt_trace_try_flip_a1); - for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) + for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) if (rcu_try_flip_waitack_needed(cpu) && per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) { RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1); @@ -798,7 +809,7 @@ rcu_try_flip_waitzero(void) /* Check to see if the sum of the "last" counters is zero. */ RCU_TRACE_ME(rcupreempt_trace_try_flip_z1); - for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) + for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) sum += RCU_DATA_CPU(cpu)->rcu_flipctr[lastidx]; if (sum != 0) { RCU_TRACE_ME(rcupreempt_trace_try_flip_ze1); @@ -813,7 +824,7 @@ rcu_try_flip_waitzero(void) smp_mb(); /* ^^^^^^^^^^^^ */ /* Call for a memory barrier from each CPU. */ - for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) { + for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) { per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed; dyntick_save_progress_counter(cpu); } @@ -833,7 +844,7 @@ rcu_try_flip_waitmb(void) int cpu; RCU_TRACE_ME(rcupreempt_trace_try_flip_m1); - for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) + for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) if (rcu_try_flip_waitmb_needed(cpu) && per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) { RCU_TRACE_ME(rcupreempt_trace_try_flip_me1); @@ -1022,7 +1033,7 @@ void rcu_offline_cpu(int cpu) RCU_DATA_CPU(cpu)->rcu_flipctr[0] = 0; RCU_DATA_CPU(cpu)->rcu_flipctr[1] = 0; - cpu_clear(cpu, rcu_cpu_online_map); + cpumask_clear_cpu(cpu, to_cpumask(rcu_cpu_online_map)); spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags); @@ -1062,7 +1073,7 @@ void __cpuinit rcu_online_cpu(int cpu) struct rcu_data *rdp; spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags); - cpu_set(cpu, rcu_cpu_online_map); + cpumask_set_cpu(cpu, to_cpumask(rcu_cpu_online_map)); spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags); /* @@ -1166,7 +1177,16 @@ EXPORT_SYMBOL_GPL(call_rcu_sched); * in -rt this does -not- necessarily result in all currently executing * interrupt -handlers- having completed. */ -synchronize_rcu_xxx(__synchronize_sched, call_rcu_sched) +void __synchronize_sched(void) +{ + struct rcu_synchronize rcu; + + init_completion(&rcu.completion); + /* Will wake me after RCU finished. */ + call_rcu_sched(&rcu.head, wakeme_after_rcu); + /* Wait for it. */ + wait_for_completion(&rcu.completion); +} EXPORT_SYMBOL_GPL(__synchronize_sched); /* @@ -1420,7 +1440,7 @@ void __init __rcu_init(void) * We don't need protection against CPU-Hotplug here * since * a) If a CPU comes online while we are iterating over the - * cpu_online_map below, we would only end up making a + * cpu_online_mask below, we would only end up making a * duplicate call to rcu_online_cpu() which sets the corresponding * CPU's mask in the rcu_cpu_online_map. * diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c index 35c2d33..7c2665c 100644 --- a/kernel/rcupreempt_trace.c +++ b/kernel/rcupreempt_trace.c @@ -149,12 +149,12 @@ static void rcupreempt_trace_sum(struct rcupreempt_trace *sp) sp->done_length += cp->done_length; sp->done_add += cp->done_add; sp->done_remove += cp->done_remove; - atomic_set(&sp->done_invoked, atomic_read(&cp->done_invoked)); + atomic_add(atomic_read(&cp->done_invoked), &sp->done_invoked); sp->rcu_check_callbacks += cp->rcu_check_callbacks; - atomic_set(&sp->rcu_try_flip_1, - atomic_read(&cp->rcu_try_flip_1)); - atomic_set(&sp->rcu_try_flip_e1, - atomic_read(&cp->rcu_try_flip_e1)); + atomic_add(atomic_read(&cp->rcu_try_flip_1), + &sp->rcu_try_flip_1); + atomic_add(atomic_read(&cp->rcu_try_flip_e1), + &sp->rcu_try_flip_e1); sp->rcu_try_flip_i1 += cp->rcu_try_flip_i1; sp->rcu_try_flip_ie1 += cp->rcu_try_flip_ie1; sp->rcu_try_flip_g1 += cp->rcu_try_flip_g1; diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 85cb905..1cff28d 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -39,6 +39,7 @@ #include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/notifier.h> +#include <linux/reboot.h> #include <linux/freezer.h> #include <linux/cpu.h> #include <linux/delay.h> @@ -108,7 +109,6 @@ struct rcu_torture { int rtort_mbtest; }; -static int fullstop = 0; /* stop generating callbacks at test end. */ static LIST_HEAD(rcu_torture_freelist); static struct rcu_torture *rcu_torture_current = NULL; static long rcu_torture_current_version = 0; @@ -136,6 +136,28 @@ static int stutter_pause_test = 0; #endif int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; +#define FULLSTOP_SHUTDOWN 1 /* Bail due to system shutdown/panic. */ +#define FULLSTOP_CLEANUP 2 /* Orderly shutdown. */ +static int fullstop; /* stop generating callbacks at test end. */ +DEFINE_MUTEX(fullstop_mutex); /* protect fullstop transitions and */ + /* spawning of kthreads. */ + +/* + * Detect and respond to a signal-based shutdown. + */ +static int +rcutorture_shutdown_notify(struct notifier_block *unused1, + unsigned long unused2, void *unused3) +{ + if (fullstop) + return NOTIFY_DONE; + mutex_lock(&fullstop_mutex); + if (!fullstop) + fullstop = FULLSTOP_SHUTDOWN; + mutex_unlock(&fullstop_mutex); + return NOTIFY_DONE; +} + /* * Allocate an element from the rcu_tortures pool. */ @@ -199,11 +221,12 @@ rcu_random(struct rcu_random_state *rrsp) static void rcu_stutter_wait(void) { - while (stutter_pause_test || !rcutorture_runnable) + while ((stutter_pause_test || !rcutorture_runnable) && !fullstop) { if (rcutorture_runnable) schedule_timeout_interruptible(1); else schedule_timeout_interruptible(round_jiffies_relative(HZ)); + } } /* @@ -599,7 +622,7 @@ rcu_torture_writer(void *arg) rcu_stutter_wait(); } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping"); - while (!kthread_should_stop()) + while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN) schedule_timeout_uninterruptible(1); return 0; } @@ -624,7 +647,7 @@ rcu_torture_fakewriter(void *arg) } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping"); - while (!kthread_should_stop()) + while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN) schedule_timeout_uninterruptible(1); return 0; } @@ -734,7 +757,7 @@ rcu_torture_reader(void *arg) VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping"); if (irqreader && cur_ops->irqcapable) del_timer_sync(&t); - while (!kthread_should_stop()) + while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN) schedule_timeout_uninterruptible(1); return 0; } @@ -831,7 +854,7 @@ rcu_torture_stats(void *arg) do { schedule_timeout_interruptible(stat_interval * HZ); rcu_torture_stats_print(); - } while (!kthread_should_stop()); + } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping"); return 0; } @@ -843,49 +866,52 @@ static int rcu_idle_cpu; /* Force all torture tasks off this CPU */ */ static void rcu_torture_shuffle_tasks(void) { - cpumask_t tmp_mask; + cpumask_var_t tmp_mask; int i; - cpus_setall(tmp_mask); + if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL)) + BUG(); + + cpumask_setall(tmp_mask); get_online_cpus(); /* No point in shuffling if there is only one online CPU (ex: UP) */ - if (num_online_cpus() == 1) { - put_online_cpus(); - return; - } + if (num_online_cpus() == 1) + goto out; if (rcu_idle_cpu != -1) - cpu_clear(rcu_idle_cpu, tmp_mask); + cpumask_clear_cpu(rcu_idle_cpu, tmp_mask); - set_cpus_allowed_ptr(current, &tmp_mask); + set_cpus_allowed_ptr(current, tmp_mask); if (reader_tasks) { for (i = 0; i < nrealreaders; i++) if (reader_tasks[i]) set_cpus_allowed_ptr(reader_tasks[i], - &tmp_mask); + tmp_mask); } if (fakewriter_tasks) { for (i = 0; i < nfakewriters; i++) if (fakewriter_tasks[i]) set_cpus_allowed_ptr(fakewriter_tasks[i], - &tmp_mask); + tmp_mask); } if (writer_task) - set_cpus_allowed_ptr(writer_task, &tmp_mask); + set_cpus_allowed_ptr(writer_task, tmp_mask); if (stats_task) - set_cpus_allowed_ptr(stats_task, &tmp_mask); + set_cpus_allowed_ptr(stats_task, tmp_mask); if (rcu_idle_cpu == -1) rcu_idle_cpu = num_online_cpus() - 1; else rcu_idle_cpu--; +out: put_online_cpus(); + free_cpumask_var(tmp_mask); } /* Shuffle tasks across CPUs, with the intent of allowing each CPU in the @@ -899,7 +925,7 @@ rcu_torture_shuffle(void *arg) do { schedule_timeout_interruptible(shuffle_interval * HZ); rcu_torture_shuffle_tasks(); - } while (!kthread_should_stop()); + } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping"); return 0; } @@ -914,10 +940,10 @@ rcu_torture_stutter(void *arg) do { schedule_timeout_interruptible(stutter * HZ); stutter_pause_test = 1; - if (!kthread_should_stop()) + if (!kthread_should_stop() && !fullstop) schedule_timeout_interruptible(stutter * HZ); stutter_pause_test = 0; - } while (!kthread_should_stop()); + } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping"); return 0; } @@ -934,12 +960,27 @@ rcu_torture_print_module_parms(char *tag) stutter, irqreader); } +static struct notifier_block rcutorture_nb = { + .notifier_call = rcutorture_shutdown_notify, +}; + static void rcu_torture_cleanup(void) { int i; - fullstop = 1; + mutex_lock(&fullstop_mutex); + if (!fullstop) { + /* If being signaled, let it happen, then exit. */ + mutex_unlock(&fullstop_mutex); + schedule_timeout_interruptible(10 * HZ); + if (cur_ops->cb_barrier != NULL) + cur_ops->cb_barrier(); + return; + } + fullstop = FULLSTOP_CLEANUP; + mutex_unlock(&fullstop_mutex); + unregister_reboot_notifier(&rcutorture_nb); if (stutter_task) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task"); kthread_stop(stutter_task); @@ -1015,6 +1056,8 @@ rcu_torture_init(void) { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &srcu_ops, &sched_ops, &sched_ops_sync, }; + mutex_lock(&fullstop_mutex); + /* Process args and tell the world that the torturer is on the job. */ for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { cur_ops = torture_ops[i]; @@ -1024,6 +1067,7 @@ rcu_torture_init(void) if (i == ARRAY_SIZE(torture_ops)) { printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n", torture_type); + mutex_unlock(&fullstop_mutex); return (-EINVAL); } if (cur_ops->init) @@ -1146,9 +1190,12 @@ rcu_torture_init(void) goto unwind; } } + register_reboot_notifier(&rcutorture_nb); + mutex_unlock(&fullstop_mutex); return 0; unwind: + mutex_unlock(&fullstop_mutex); rcu_torture_cleanup(); return firsterr; } diff --git a/kernel/rcutree.c b/kernel/rcutree.c new file mode 100644 index 0000000..f2d8638 --- /dev/null +++ b/kernel/rcutree.c @@ -0,0 +1,1532 @@ +/* + * Read-Copy Update mechanism for mutual exclusion + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2008 + * + * Authors: Dipankar Sarma <dipankar@in.ibm.com> + * Manfred Spraul <manfred@colorfullife.com> + * Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version + * + * Based on the original work by Paul McKenney <paulmck@us.ibm.com> + * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/rcupdate.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <asm/atomic.h> +#include <linux/bitops.h> +#include <linux/module.h> +#include <linux/completion.h> +#include <linux/moduleparam.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/mutex.h> +#include <linux/time.h> + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static struct lock_class_key rcu_lock_key; +struct lockdep_map rcu_lock_map = + STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key); +EXPORT_SYMBOL_GPL(rcu_lock_map); +#endif + +/* Data structures. */ + +#define RCU_STATE_INITIALIZER(name) { \ + .level = { &name.node[0] }, \ + .levelcnt = { \ + NUM_RCU_LVL_0, /* root of hierarchy. */ \ + NUM_RCU_LVL_1, \ + NUM_RCU_LVL_2, \ + NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \ + }, \ + .signaled = RCU_SIGNAL_INIT, \ + .gpnum = -300, \ + .completed = -300, \ + .onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \ + .fqslock = __SPIN_LOCK_UNLOCKED(&name.fqslock), \ + .n_force_qs = 0, \ + .n_force_qs_ngp = 0, \ +} + +struct rcu_state rcu_state = RCU_STATE_INITIALIZER(rcu_state); +DEFINE_PER_CPU(struct rcu_data, rcu_data); + +struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state); +DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); + +#ifdef CONFIG_NO_HZ +DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { + .dynticks_nesting = 1, + .dynticks = 1, +}; +#endif /* #ifdef CONFIG_NO_HZ */ + +static int blimit = 10; /* Maximum callbacks per softirq. */ +static int qhimark = 10000; /* If this many pending, ignore blimit. */ +static int qlowmark = 100; /* Once only this many pending, use blimit. */ + +static void force_quiescent_state(struct rcu_state *rsp, int relaxed); + +/* + * Return the number of RCU batches processed thus far for debug & stats. + */ +long rcu_batches_completed(void) +{ + return rcu_state.completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed); + +/* + * Return the number of RCU BH batches processed thus far for debug & stats. + */ +long rcu_batches_completed_bh(void) +{ + return rcu_bh_state.completed; +} +EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); + +/* + * Does the CPU have callbacks ready to be invoked? + */ +static int +cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) +{ + return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]; +} + +/* + * Does the current CPU require a yet-as-unscheduled grace period? + */ +static int +cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) +{ + /* ACCESS_ONCE() because we are accessing outside of lock. */ + return *rdp->nxttail[RCU_DONE_TAIL] && + ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum); +} + +/* + * Return the root node of the specified rcu_state structure. + */ +static struct rcu_node *rcu_get_root(struct rcu_state *rsp) +{ + return &rsp->node[0]; +} + +#ifdef CONFIG_SMP + +/* + * If the specified CPU is offline, tell the caller that it is in + * a quiescent state. Otherwise, whack it with a reschedule IPI. + * Grace periods can end up waiting on an offline CPU when that + * CPU is in the process of coming online -- it will be added to the + * rcu_node bitmasks before it actually makes it online. The same thing + * can happen while a CPU is in the process of coming online. Because this + * race is quite rare, we check for it after detecting that the grace + * period has been delayed rather than checking each and every CPU + * each and every time we start a new grace period. + */ +static int rcu_implicit_offline_qs(struct rcu_data *rdp) +{ + /* + * If the CPU is offline, it is in a quiescent state. We can + * trust its state not to change because interrupts are disabled. + */ + if (cpu_is_offline(rdp->cpu)) { + rdp->offline_fqs++; + return 1; + } + + /* The CPU is online, so send it a reschedule IPI. */ + if (rdp->cpu != smp_processor_id()) + smp_send_reschedule(rdp->cpu); + else + set_need_resched(); + rdp->resched_ipi++; + return 0; +} + +#endif /* #ifdef CONFIG_SMP */ + +#ifdef CONFIG_NO_HZ +static DEFINE_RATELIMIT_STATE(rcu_rs, 10 * HZ, 5); + +/** + * rcu_enter_nohz - inform RCU that current CPU is entering nohz + * + * Enter nohz mode, in other words, -leave- the mode in which RCU + * read-side critical sections can occur. (Though RCU read-side + * critical sections can occur in irq handlers in nohz mode, a possibility + * handled by rcu_irq_enter() and rcu_irq_exit()). + */ +void rcu_enter_nohz(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + + smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + rdtp->dynticks++; + rdtp->dynticks_nesting--; + WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs); + local_irq_restore(flags); +} + +/* + * rcu_exit_nohz - inform RCU that current CPU is leaving nohz + * + * Exit nohz mode, in other words, -enter- the mode in which RCU + * read-side critical sections normally occur. + */ +void rcu_exit_nohz(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + rdtp->dynticks++; + rdtp->dynticks_nesting++; + WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs); + local_irq_restore(flags); + smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ +} + +/** + * rcu_nmi_enter - inform RCU of entry to NMI context + * + * If the CPU was idle with dynamic ticks active, and there is no + * irq handler running, this updates rdtp->dynticks_nmi to let the + * RCU grace-period handling know that the CPU is active. + */ +void rcu_nmi_enter(void) +{ + struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); + + if (rdtp->dynticks & 0x1) + return; + rdtp->dynticks_nmi++; + WARN_ON_RATELIMIT(!(rdtp->dynticks_nmi & 0x1), &rcu_rs); + smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ +} + +/** + * rcu_nmi_exit - inform RCU of exit from NMI context + * + * If the CPU was idle with dynamic ticks active, and there is no + * irq handler running, this updates rdtp->dynticks_nmi to let the + * RCU grace-period handling know that the CPU is no longer active. + */ +void rcu_nmi_exit(void) +{ + struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); + + if (rdtp->dynticks & 0x1) + return; + smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ + rdtp->dynticks_nmi++; + WARN_ON_RATELIMIT(rdtp->dynticks_nmi & 0x1, &rcu_rs); +} + +/** + * rcu_irq_enter - inform RCU of entry to hard irq context + * + * If the CPU was idle with dynamic ticks active, this updates the + * rdtp->dynticks to let the RCU handling know that the CPU is active. + */ +void rcu_irq_enter(void) +{ + struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); + + if (rdtp->dynticks_nesting++) + return; + rdtp->dynticks++; + WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs); + smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */ +} + +/** + * rcu_irq_exit - inform RCU of exit from hard irq context + * + * If the CPU was idle with dynamic ticks active, update the rdp->dynticks + * to put let the RCU handling be aware that the CPU is going back to idle + * with no ticks. + */ +void rcu_irq_exit(void) +{ + struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks); + + if (--rdtp->dynticks_nesting) + return; + smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */ + rdtp->dynticks++; + WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs); + + /* If the interrupt queued a callback, get out of dyntick mode. */ + if (__get_cpu_var(rcu_data).nxtlist || + __get_cpu_var(rcu_bh_data).nxtlist) + set_need_resched(); +} + +/* + * Record the specified "completed" value, which is later used to validate + * dynticks counter manipulations. Specify "rsp->completed - 1" to + * unconditionally invalidate any future dynticks manipulations (which is + * useful at the beginning of a grace period). + */ +static void dyntick_record_completed(struct rcu_state *rsp, long comp) +{ + rsp->dynticks_completed = comp; +} + +#ifdef CONFIG_SMP + +/* + * Recall the previously recorded value of the completion for dynticks. + */ +static long dyntick_recall_completed(struct rcu_state *rsp) +{ + return rsp->dynticks_completed; +} + +/* + * Snapshot the specified CPU's dynticks counter so that we can later + * credit them with an implicit quiescent state. Return 1 if this CPU + * is already in a quiescent state courtesy of dynticks idle mode. + */ +static int dyntick_save_progress_counter(struct rcu_data *rdp) +{ + int ret; + int snap; + int snap_nmi; + + snap = rdp->dynticks->dynticks; + snap_nmi = rdp->dynticks->dynticks_nmi; + smp_mb(); /* Order sampling of snap with end of grace period. */ + rdp->dynticks_snap = snap; + rdp->dynticks_nmi_snap = snap_nmi; + ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0); + if (ret) + rdp->dynticks_fqs++; + return ret; +} + +/* + * Return true if the specified CPU has passed through a quiescent + * state by virtue of being in or having passed through an dynticks + * idle state since the last call to dyntick_save_progress_counter() + * for this same CPU. + */ +static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) +{ + long curr; + long curr_nmi; + long snap; + long snap_nmi; + + curr = rdp->dynticks->dynticks; + snap = rdp->dynticks_snap; + curr_nmi = rdp->dynticks->dynticks_nmi; + snap_nmi = rdp->dynticks_nmi_snap; + smp_mb(); /* force ordering with cpu entering/leaving dynticks. */ + + /* + * If the CPU passed through or entered a dynticks idle phase with + * no active irq/NMI handlers, then we can safely pretend that the CPU + * already acknowledged the request to pass through a quiescent + * state. Either way, that CPU cannot possibly be in an RCU + * read-side critical section that started before the beginning + * of the current RCU grace period. + */ + if ((curr != snap || (curr & 0x1) == 0) && + (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) { + rdp->dynticks_fqs++; + return 1; + } + + /* Go check for the CPU being offline. */ + return rcu_implicit_offline_qs(rdp); +} + +#endif /* #ifdef CONFIG_SMP */ + +#else /* #ifdef CONFIG_NO_HZ */ + +static void dyntick_record_completed(struct rcu_state *rsp, long comp) +{ +} + +#ifdef CONFIG_SMP + +/* + * If there are no dynticks, then the only way that a CPU can passively + * be in a quiescent state is to be offline. Unlike dynticks idle, which + * is a point in time during the prior (already finished) grace period, + * an offline CPU is always in a quiescent state, and thus can be + * unconditionally applied. So just return the current value of completed. + */ +static long dyntick_recall_completed(struct rcu_state *rsp) +{ + return rsp->completed; +} + +static int dyntick_save_progress_counter(struct rcu_data *rdp) +{ + return 0; +} + +static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) +{ + return rcu_implicit_offline_qs(rdp); +} + +#endif /* #ifdef CONFIG_SMP */ + +#endif /* #else #ifdef CONFIG_NO_HZ */ + +#ifdef CONFIG_RCU_CPU_STALL_DETECTOR + +static void record_gp_stall_check_time(struct rcu_state *rsp) +{ + rsp->gp_start = jiffies; + rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK; +} + +static void print_other_cpu_stall(struct rcu_state *rsp) +{ + int cpu; + long delta; + unsigned long flags; + struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1]; + struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES]; + + /* Only let one CPU complain about others per time interval. */ + + spin_lock_irqsave(&rnp->lock, flags); + delta = jiffies - rsp->jiffies_stall; + if (delta < RCU_STALL_RAT_DELAY || rsp->gpnum == rsp->completed) { + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK; + spin_unlock_irqrestore(&rnp->lock, flags); + + /* OK, time to rat on our buddy... */ + + printk(KERN_ERR "INFO: RCU detected CPU stalls:"); + for (; rnp_cur < rnp_end; rnp_cur++) { + if (rnp_cur->qsmask == 0) + continue; + for (cpu = 0; cpu <= rnp_cur->grphi - rnp_cur->grplo; cpu++) + if (rnp_cur->qsmask & (1UL << cpu)) + printk(" %d", rnp_cur->grplo + cpu); + } + printk(" (detected by %d, t=%ld jiffies)\n", + smp_processor_id(), (long)(jiffies - rsp->gp_start)); + force_quiescent_state(rsp, 0); /* Kick them all. */ +} + +static void print_cpu_stall(struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_node *rnp = rcu_get_root(rsp); + + printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n", + smp_processor_id(), jiffies - rsp->gp_start); + dump_stack(); + spin_lock_irqsave(&rnp->lock, flags); + if ((long)(jiffies - rsp->jiffies_stall) >= 0) + rsp->jiffies_stall = + jiffies + RCU_SECONDS_TILL_STALL_RECHECK; + spin_unlock_irqrestore(&rnp->lock, flags); + set_need_resched(); /* kick ourselves to get things going. */ +} + +static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) +{ + long delta; + struct rcu_node *rnp; + + delta = jiffies - rsp->jiffies_stall; + rnp = rdp->mynode; + if ((rnp->qsmask & rdp->grpmask) && delta >= 0) { + + /* We haven't checked in, so go dump stack. */ + print_cpu_stall(rsp); + + } else if (rsp->gpnum != rsp->completed && + delta >= RCU_STALL_RAT_DELAY) { + + /* They had two time units to dump stack, so complain. */ + print_other_cpu_stall(rsp); + } +} + +#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ + +static void record_gp_stall_check_time(struct rcu_state *rsp) +{ +} + +static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) +{ +} + +#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ + +/* + * Update CPU-local rcu_data state to record the newly noticed grace period. + * This is used both when we started the grace period and when we notice + * that someone else started the grace period. + */ +static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp) +{ + rdp->qs_pending = 1; + rdp->passed_quiesc = 0; + rdp->gpnum = rsp->gpnum; + rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + + RCU_JIFFIES_TILL_FORCE_QS; +} + +/* + * Did someone else start a new RCU grace period start since we last + * checked? Update local state appropriately if so. Must be called + * on the CPU corresponding to rdp. + */ +static int +check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + int ret = 0; + + local_irq_save(flags); + if (rdp->gpnum != rsp->gpnum) { + note_new_gpnum(rsp, rdp); + ret = 1; + } + local_irq_restore(flags); + return ret; +} + +/* + * Start a new RCU grace period if warranted, re-initializing the hierarchy + * in preparation for detecting the next grace period. The caller must hold + * the root node's ->lock, which is released before return. Hard irqs must + * be disabled. + */ +static void +rcu_start_gp(struct rcu_state *rsp, unsigned long flags) + __releases(rcu_get_root(rsp)->lock) +{ + struct rcu_data *rdp = rsp->rda[smp_processor_id()]; + struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp_cur; + struct rcu_node *rnp_end; + + if (!cpu_needs_another_gp(rsp, rdp)) { + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + + /* Advance to a new grace period and initialize state. */ + rsp->gpnum++; + rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */ + rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; + rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + + RCU_JIFFIES_TILL_FORCE_QS; + record_gp_stall_check_time(rsp); + dyntick_record_completed(rsp, rsp->completed - 1); + note_new_gpnum(rsp, rdp); + + /* + * Because we are first, we know that all our callbacks will + * be covered by this upcoming grace period, even the ones + * that were registered arbitrarily recently. + */ + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + /* Special-case the common single-level case. */ + if (NUM_RCU_NODES == 1) { + rnp->qsmask = rnp->qsmaskinit; + rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */ + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + + spin_unlock(&rnp->lock); /* leave irqs disabled. */ + + + /* Exclude any concurrent CPU-hotplug operations. */ + spin_lock(&rsp->onofflock); /* irqs already disabled. */ + + /* + * Set the quiescent-state-needed bits in all the non-leaf RCU + * nodes for all currently online CPUs. This operation relies + * on the layout of the hierarchy within the rsp->node[] array. + * Note that other CPUs will access only the leaves of the + * hierarchy, which still indicate that no grace period is in + * progress. In addition, we have excluded CPU-hotplug operations. + * + * We therefore do not need to hold any locks. Any required + * memory barriers will be supplied by the locks guarding the + * leaf rcu_nodes in the hierarchy. + */ + + rnp_end = rsp->level[NUM_RCU_LVLS - 1]; + for (rnp_cur = &rsp->node[0]; rnp_cur < rnp_end; rnp_cur++) + rnp_cur->qsmask = rnp_cur->qsmaskinit; + + /* + * Now set up the leaf nodes. Here we must be careful. First, + * we need to hold the lock in order to exclude other CPUs, which + * might be contending for the leaf nodes' locks. Second, as + * soon as we initialize a given leaf node, its CPUs might run + * up the rest of the hierarchy. We must therefore acquire locks + * for each node that we touch during this stage. (But we still + * are excluding CPU-hotplug operations.) + * + * Note that the grace period cannot complete until we finish + * the initialization process, as there will be at least one + * qsmask bit set in the root node until that time, namely the + * one corresponding to this CPU. + */ + rnp_end = &rsp->node[NUM_RCU_NODES]; + rnp_cur = rsp->level[NUM_RCU_LVLS - 1]; + for (; rnp_cur < rnp_end; rnp_cur++) { + spin_lock(&rnp_cur->lock); /* irqs already disabled. */ + rnp_cur->qsmask = rnp_cur->qsmaskinit; + spin_unlock(&rnp_cur->lock); /* irqs already disabled. */ + } + + rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */ + spin_unlock_irqrestore(&rsp->onofflock, flags); +} + +/* + * Advance this CPU's callbacks, but only if the current grace period + * has ended. This may be called only from the CPU to whom the rdp + * belongs. + */ +static void +rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp) +{ + long completed_snap; + unsigned long flags; + + local_irq_save(flags); + completed_snap = ACCESS_ONCE(rsp->completed); /* outside of lock. */ + + /* Did another grace period end? */ + if (rdp->completed != completed_snap) { + + /* Advance callbacks. No harm if list empty. */ + rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL]; + rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL]; + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + /* Remember that we saw this grace-period completion. */ + rdp->completed = completed_snap; + } + local_irq_restore(flags); +} + +/* + * Similar to cpu_quiet(), for which it is a helper function. Allows + * a group of CPUs to be quieted at one go, though all the CPUs in the + * group must be represented by the same leaf rcu_node structure. + * That structure's lock must be held upon entry, and it is released + * before return. + */ +static void +cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp, + unsigned long flags) + __releases(rnp->lock) +{ + /* Walk up the rcu_node hierarchy. */ + for (;;) { + if (!(rnp->qsmask & mask)) { + + /* Our bit has already been cleared, so done. */ + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + rnp->qsmask &= ~mask; + if (rnp->qsmask != 0) { + + /* Other bits still set at this level, so done. */ + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + mask = rnp->grpmask; + if (rnp->parent == NULL) { + + /* No more levels. Exit loop holding root lock. */ + + break; + } + spin_unlock_irqrestore(&rnp->lock, flags); + rnp = rnp->parent; + spin_lock_irqsave(&rnp->lock, flags); + } + + /* + * Get here if we are the last CPU to pass through a quiescent + * state for this grace period. Clean up and let rcu_start_gp() + * start up the next grace period if one is needed. Note that + * we still hold rnp->lock, as required by rcu_start_gp(), which + * will release it. + */ + rsp->completed = rsp->gpnum; + rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]); + rcu_start_gp(rsp, flags); /* releases rnp->lock. */ +} + +/* + * Record a quiescent state for the specified CPU, which must either be + * the current CPU or an offline CPU. The lastcomp argument is used to + * make sure we are still in the grace period of interest. We don't want + * to end the current grace period based on quiescent states detected in + * an earlier grace period! + */ +static void +cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp) +{ + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp; + + rnp = rdp->mynode; + spin_lock_irqsave(&rnp->lock, flags); + if (lastcomp != ACCESS_ONCE(rsp->completed)) { + + /* + * Someone beat us to it for this grace period, so leave. + * The race with GP start is resolved by the fact that we + * hold the leaf rcu_node lock, so that the per-CPU bits + * cannot yet be initialized -- so we would simply find our + * CPU's bit already cleared in cpu_quiet_msk() if this race + * occurred. + */ + rdp->passed_quiesc = 0; /* try again later! */ + spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + mask = rdp->grpmask; + if ((rnp->qsmask & mask) == 0) { + spin_unlock_irqrestore(&rnp->lock, flags); + } else { + rdp->qs_pending = 0; + + /* + * This GP can't end until cpu checks in, so all of our + * callbacks can be processed during the next GP. + */ + rdp = rsp->rda[smp_processor_id()]; + rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + + cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */ + } +} + +/* + * Check to see if there is a new grace period of which this CPU + * is not yet aware, and if so, set up local rcu_data state for it. + * Otherwise, see if this CPU has just passed through its first + * quiescent state for this grace period, and record that fact if so. + */ +static void +rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) +{ + /* If there is now a new grace period, record and return. */ + if (check_for_new_grace_period(rsp, rdp)) + return; + + /* + * Does this CPU still need to do its part for current grace period? + * If no, return and let the other CPUs do their part as well. + */ + if (!rdp->qs_pending) + return; + + /* + * Was there a quiescent state since the beginning of the grace + * period? If no, then exit and wait for the next call. + */ + if (!rdp->passed_quiesc) + return; + + /* Tell RCU we are done (but cpu_quiet() will be the judge of that). */ + cpu_quiet(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy + * and move all callbacks from the outgoing CPU to the current one. + */ +static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) +{ + int i; + unsigned long flags; + long lastcomp; + unsigned long mask; + struct rcu_data *rdp = rsp->rda[cpu]; + struct rcu_data *rdp_me; + struct rcu_node *rnp; + + /* Exclude any attempts to start a new grace period. */ + spin_lock_irqsave(&rsp->onofflock, flags); + + /* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */ + rnp = rdp->mynode; + mask = rdp->grpmask; /* rnp->grplo is constant. */ + do { + spin_lock(&rnp->lock); /* irqs already disabled. */ + rnp->qsmaskinit &= ~mask; + if (rnp->qsmaskinit != 0) { + spin_unlock(&rnp->lock); /* irqs already disabled. */ + break; + } + mask = rnp->grpmask; + spin_unlock(&rnp->lock); /* irqs already disabled. */ + rnp = rnp->parent; + } while (rnp != NULL); + lastcomp = rsp->completed; + + spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ + + /* Being offline is a quiescent state, so go record it. */ + cpu_quiet(cpu, rsp, rdp, lastcomp); + + /* + * Move callbacks from the outgoing CPU to the running CPU. + * Note that the outgoing CPU is now quiscent, so it is now + * (uncharacteristically) safe to access it rcu_data structure. + * Note also that we must carefully retain the order of the + * outgoing CPU's callbacks in order for rcu_barrier() to work + * correctly. Finally, note that we start all the callbacks + * afresh, even those that have passed through a grace period + * and are therefore ready to invoke. The theory is that hotplug + * events are rare, and that if they are frequent enough to + * indefinitely delay callbacks, you have far worse things to + * be worrying about. + */ + rdp_me = rsp->rda[smp_processor_id()]; + if (rdp->nxtlist != NULL) { + *rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist; + rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; + rdp_me->qlen += rdp->qlen; + rdp->qlen = 0; + } + local_irq_restore(flags); +} + +/* + * Remove the specified CPU from the RCU hierarchy and move any pending + * callbacks that it might have to the current CPU. This code assumes + * that at least one CPU in the system will remain running at all times. + * Any attempt to offline -all- CPUs is likely to strand RCU callbacks. + */ +static void rcu_offline_cpu(int cpu) +{ + __rcu_offline_cpu(cpu, &rcu_state); + __rcu_offline_cpu(cpu, &rcu_bh_state); +} + +#else /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void rcu_offline_cpu(int cpu) +{ +} + +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ + +/* + * Invoke any RCU callbacks that have made it to the end of their grace + * period. Thottle as specified by rdp->blimit. + */ +static void rcu_do_batch(struct rcu_data *rdp) +{ + unsigned long flags; + struct rcu_head *next, *list, **tail; + int count; + + /* If no callbacks are ready, just return.*/ + if (!cpu_has_callbacks_ready_to_invoke(rdp)) + return; + + /* + * Extract the list of ready callbacks, disabling to prevent + * races with call_rcu() from interrupt handlers. + */ + local_irq_save(flags); + list = rdp->nxtlist; + rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL]; + *rdp->nxttail[RCU_DONE_TAIL] = NULL; + tail = rdp->nxttail[RCU_DONE_TAIL]; + for (count = RCU_NEXT_SIZE - 1; count >= 0; count--) + if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL]) + rdp->nxttail[count] = &rdp->nxtlist; + local_irq_restore(flags); + + /* Invoke callbacks. */ + count = 0; + while (list) { + next = list->next; + prefetch(next); + list->func(list); + list = next; + if (++count >= rdp->blimit) + break; + } + + local_irq_save(flags); + + /* Update count, and requeue any remaining callbacks. */ + rdp->qlen -= count; + if (list != NULL) { + *tail = rdp->nxtlist; + rdp->nxtlist = list; + for (count = 0; count < RCU_NEXT_SIZE; count++) + if (&rdp->nxtlist == rdp->nxttail[count]) + rdp->nxttail[count] = tail; + else + break; + } + + /* Reinstate batch limit if we have worked down the excess. */ + if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark) + rdp->blimit = blimit; + + local_irq_restore(flags); + + /* Re-raise the RCU softirq if there are callbacks remaining. */ + if (cpu_has_callbacks_ready_to_invoke(rdp)) + raise_softirq(RCU_SOFTIRQ); +} + +/* + * Check to see if this CPU is in a non-context-switch quiescent state + * (user mode or idle loop for rcu, non-softirq execution for rcu_bh). + * Also schedule the RCU softirq handler. + * + * This function must be called with hardirqs disabled. It is normally + * invoked from the scheduling-clock interrupt. If rcu_pending returns + * false, there is no point in invoking rcu_check_callbacks(). + */ +void rcu_check_callbacks(int cpu, int user) +{ + if (user || + (idle_cpu(cpu) && !in_softirq() && + hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + + /* + * Get here if this CPU took its interrupt from user + * mode or from the idle loop, and if this is not a + * nested interrupt. In this case, the CPU is in + * a quiescent state, so count it. + * + * No memory barrier is required here because both + * rcu_qsctr_inc() and rcu_bh_qsctr_inc() reference + * only CPU-local variables that other CPUs neither + * access nor modify, at least not while the corresponding + * CPU is online. + */ + + rcu_qsctr_inc(cpu); + rcu_bh_qsctr_inc(cpu); + + } else if (!in_softirq()) { + + /* + * Get here if this CPU did not take its interrupt from + * softirq, in other words, if it is not interrupting + * a rcu_bh read-side critical section. This is an _bh + * critical section, so count it. + */ + + rcu_bh_qsctr_inc(cpu); + } + raise_softirq(RCU_SOFTIRQ); +} + +#ifdef CONFIG_SMP + +/* + * Scan the leaf rcu_node structures, processing dyntick state for any that + * have not yet encountered a quiescent state, using the function specified. + * Returns 1 if the current grace period ends while scanning (possibly + * because we made it end). + */ +static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp, + int (*f)(struct rcu_data *)) +{ + unsigned long bit; + int cpu; + unsigned long flags; + unsigned long mask; + struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1]; + struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES]; + + for (; rnp_cur < rnp_end; rnp_cur++) { + mask = 0; + spin_lock_irqsave(&rnp_cur->lock, flags); + if (rsp->completed != lastcomp) { + spin_unlock_irqrestore(&rnp_cur->lock, flags); + return 1; + } + if (rnp_cur->qsmask == 0) { + spin_unlock_irqrestore(&rnp_cur->lock, flags); + continue; + } + cpu = rnp_cur->grplo; + bit = 1; + for (; cpu <= rnp_cur->grphi; cpu++, bit <<= 1) { + if ((rnp_cur->qsmask & bit) != 0 && f(rsp->rda[cpu])) + mask |= bit; + } + if (mask != 0 && rsp->completed == lastcomp) { + + /* cpu_quiet_msk() releases rnp_cur->lock. */ + cpu_quiet_msk(mask, rsp, rnp_cur, flags); + continue; + } + spin_unlock_irqrestore(&rnp_cur->lock, flags); + } + return 0; +} + +/* + * Force quiescent states on reluctant CPUs, and also detect which + * CPUs are in dyntick-idle mode. + */ +static void force_quiescent_state(struct rcu_state *rsp, int relaxed) +{ + unsigned long flags; + long lastcomp; + struct rcu_data *rdp = rsp->rda[smp_processor_id()]; + struct rcu_node *rnp = rcu_get_root(rsp); + u8 signaled; + + if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) + return; /* No grace period in progress, nothing to force. */ + if (!spin_trylock_irqsave(&rsp->fqslock, flags)) { + rsp->n_force_qs_lh++; /* Inexact, can lose counts. Tough! */ + return; /* Someone else is already on the job. */ + } + if (relaxed && + (long)(rsp->jiffies_force_qs - jiffies) >= 0 && + (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) >= 0) + goto unlock_ret; /* no emergency and done recently. */ + rsp->n_force_qs++; + spin_lock(&rnp->lock); + lastcomp = rsp->completed; + signaled = rsp->signaled; + rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; + rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending + + RCU_JIFFIES_TILL_FORCE_QS; + if (lastcomp == rsp->gpnum) { + rsp->n_force_qs_ngp++; + spin_unlock(&rnp->lock); + goto unlock_ret; /* no GP in progress, time updated. */ + } + spin_unlock(&rnp->lock); + switch (signaled) { + case RCU_GP_INIT: + + break; /* grace period still initializing, ignore. */ + + case RCU_SAVE_DYNTICK: + + if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK) + break; /* So gcc recognizes the dead code. */ + + /* Record dyntick-idle state. */ + if (rcu_process_dyntick(rsp, lastcomp, + dyntick_save_progress_counter)) + goto unlock_ret; + + /* Update state, record completion counter. */ + spin_lock(&rnp->lock); + if (lastcomp == rsp->completed) { + rsp->signaled = RCU_FORCE_QS; + dyntick_record_completed(rsp, lastcomp); + } + spin_unlock(&rnp->lock); + break; + + case RCU_FORCE_QS: + + /* Check dyntick-idle state, send IPI to laggarts. */ + if (rcu_process_dyntick(rsp, dyntick_recall_completed(rsp), + rcu_implicit_dynticks_qs)) + goto unlock_ret; + + /* Leave state in case more forcing is required. */ + + break; + } +unlock_ret: + spin_unlock_irqrestore(&rsp->fqslock, flags); +} + +#else /* #ifdef CONFIG_SMP */ + +static void force_quiescent_state(struct rcu_state *rsp, int relaxed) +{ + set_need_resched(); +} + +#endif /* #else #ifdef CONFIG_SMP */ + +/* + * This does the RCU processing work from softirq context for the + * specified rcu_state and rcu_data structures. This may be called + * only from the CPU to whom the rdp belongs. + */ +static void +__rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +{ + unsigned long flags; + + /* + * If an RCU GP has gone long enough, go check for dyntick + * idle CPUs and, if needed, send resched IPIs. + */ + if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || + (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0) + force_quiescent_state(rsp, 1); + + /* + * Advance callbacks in response to end of earlier grace + * period that some other CPU ended. + */ + rcu_process_gp_end(rsp, rdp); + + /* Update RCU state based on any recent quiescent states. */ + rcu_check_quiescent_state(rsp, rdp); + + /* Does this CPU require a not-yet-started grace period? */ + if (cpu_needs_another_gp(rsp, rdp)) { + spin_lock_irqsave(&rcu_get_root(rsp)->lock, flags); + rcu_start_gp(rsp, flags); /* releases above lock */ + } + + /* If there are callbacks ready, invoke them. */ + rcu_do_batch(rdp); +} + +/* + * Do softirq processing for the current CPU. + */ +static void rcu_process_callbacks(struct softirq_action *unused) +{ + /* + * Memory references from any prior RCU read-side critical sections + * executed by the interrupted code must be seen before any RCU + * grace-period manipulations below. + */ + smp_mb(); /* See above block comment. */ + + __rcu_process_callbacks(&rcu_state, &__get_cpu_var(rcu_data)); + __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data)); + + /* + * Memory references from any later RCU read-side critical sections + * executed by the interrupted code must be seen after any RCU + * grace-period manipulations above. + */ + smp_mb(); /* See above block comment. */ +} + +static void +__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), + struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_data *rdp; + + head->func = func; + head->next = NULL; + + smp_mb(); /* Ensure RCU update seen before callback registry. */ + + /* + * Opportunistically note grace-period endings and beginnings. + * Note that we might see a beginning right after we see an + * end, but never vice versa, since this CPU has to pass through + * a quiescent state betweentimes. + */ + local_irq_save(flags); + rdp = rsp->rda[smp_processor_id()]; + rcu_process_gp_end(rsp, rdp); + check_for_new_grace_period(rsp, rdp); + + /* Add the callback to our list. */ + *rdp->nxttail[RCU_NEXT_TAIL] = head; + rdp->nxttail[RCU_NEXT_TAIL] = &head->next; + + /* Start a new grace period if one not already started. */ + if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) { + unsigned long nestflag; + struct rcu_node *rnp_root = rcu_get_root(rsp); + + spin_lock_irqsave(&rnp_root->lock, nestflag); + rcu_start_gp(rsp, nestflag); /* releases rnp_root->lock. */ + } + + /* Force the grace period if too many callbacks or too long waiting. */ + if (unlikely(++rdp->qlen > qhimark)) { + rdp->blimit = LONG_MAX; + force_quiescent_state(rsp, 0); + } else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || + (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0) + force_quiescent_state(rsp, 1); + local_irq_restore(flags); +} + +/* + * Queue an RCU callback for invocation after a grace period. + */ +void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_state); +} +EXPORT_SYMBOL_GPL(call_rcu); + +/* + * Queue an RCU for invocation after a quicker grace period. + */ +void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + __call_rcu(head, func, &rcu_bh_state); +} +EXPORT_SYMBOL_GPL(call_rcu_bh); + +/* + * Check to see if there is any immediate RCU-related work to be done + * by the current CPU, for the specified type of RCU, returning 1 if so. + * The checks are in order of increasing expense: checks that can be + * carried out against CPU-local state are performed first. However, + * we must check for CPU stalls first, else we might not get a chance. + */ +static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) +{ + rdp->n_rcu_pending++; + + /* Check for CPU stalls, if enabled. */ + check_cpu_stall(rsp, rdp); + + /* Is the RCU core waiting for a quiescent state from this CPU? */ + if (rdp->qs_pending) + return 1; + + /* Does this CPU have callbacks ready to invoke? */ + if (cpu_has_callbacks_ready_to_invoke(rdp)) + return 1; + + /* Has RCU gone idle with this CPU needing another grace period? */ + if (cpu_needs_another_gp(rsp, rdp)) + return 1; + + /* Has another RCU grace period completed? */ + if (ACCESS_ONCE(rsp->completed) != rdp->completed) /* outside of lock */ + return 1; + + /* Has a new RCU grace period started? */ + if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) /* outside of lock */ + return 1; + + /* Has an RCU GP gone long enough to send resched IPIs &c? */ + if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) && + ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 || + (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)) + return 1; + + /* nothing to do */ + return 0; +} + +/* + * Check to see if there is any immediate RCU-related work to be done + * by the current CPU, returning 1 if so. This function is part of the + * RCU implementation; it is -not- an exported member of the RCU API. + */ +int rcu_pending(int cpu) +{ + return __rcu_pending(&rcu_state, &per_cpu(rcu_data, cpu)) || + __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, cpu)); +} + +/* + * Check to see if any future RCU-related work will need to be done + * by the current CPU, even if none need be done immediately, returning + * 1 if so. This function is part of the RCU implementation; it is -not- + * an exported member of the RCU API. + */ +int rcu_needs_cpu(int cpu) +{ + /* RCU callbacks either ready or pending? */ + return per_cpu(rcu_data, cpu).nxtlist || + per_cpu(rcu_bh_data, cpu).nxtlist; +} + +/* + * Initialize a CPU's per-CPU RCU data. We take this "scorched earth" + * approach so that we don't have to worry about how long the CPU has + * been gone, or whether it ever was online previously. We do trust the + * ->mynode field, as it is constant for a given struct rcu_data and + * initialized during early boot. + * + * Note that only one online or offline event can be happening at a given + * time. Note also that we can accept some slop in the rsp->completed + * access due to the fact that this CPU cannot possibly have any RCU + * callbacks in flight yet. + */ +static void +rcu_init_percpu_data(int cpu, struct rcu_state *rsp) +{ + unsigned long flags; + int i; + long lastcomp; + unsigned long mask; + struct rcu_data *rdp = rsp->rda[cpu]; + struct rcu_node *rnp = rcu_get_root(rsp); + + /* Set up local state, ensuring consistent view of global state. */ + spin_lock_irqsave(&rnp->lock, flags); + lastcomp = rsp->completed; + rdp->completed = lastcomp; + rdp->gpnum = lastcomp; + rdp->passed_quiesc = 0; /* We could be racing with new GP, */ + rdp->qs_pending = 1; /* so set up to respond to current GP. */ + rdp->beenonline = 1; /* We have now been online. */ + rdp->passed_quiesc_completed = lastcomp - 1; + rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; + rdp->qlen = 0; + rdp->blimit = blimit; +#ifdef CONFIG_NO_HZ + rdp->dynticks = &per_cpu(rcu_dynticks, cpu); +#endif /* #ifdef CONFIG_NO_HZ */ + rdp->cpu = cpu; + spin_unlock(&rnp->lock); /* irqs remain disabled. */ + + /* + * A new grace period might start here. If so, we won't be part + * of it, but that is OK, as we are currently in a quiescent state. + */ + + /* Exclude any attempts to start a new GP on large systems. */ + spin_lock(&rsp->onofflock); /* irqs already disabled. */ + + /* Add CPU to rcu_node bitmasks. */ + rnp = rdp->mynode; + mask = rdp->grpmask; + do { + /* Exclude any attempts to start a new GP on small systems. */ + spin_lock(&rnp->lock); /* irqs already disabled. */ + rnp->qsmaskinit |= mask; + mask = rnp->grpmask; + spin_unlock(&rnp->lock); /* irqs already disabled. */ + rnp = rnp->parent; + } while (rnp != NULL && !(rnp->qsmaskinit & mask)); + + spin_unlock(&rsp->onofflock); /* irqs remain disabled. */ + + /* + * A new grace period might start here. If so, we will be part of + * it, and its gpnum will be greater than ours, so we will + * participate. It is also possible for the gpnum to have been + * incremented before this function was called, and the bitmasks + * to not be filled out until now, in which case we will also + * participate due to our gpnum being behind. + */ + + /* Since it is coming online, the CPU is in a quiescent state. */ + cpu_quiet(cpu, rsp, rdp, lastcomp); + local_irq_restore(flags); +} + +static void __cpuinit rcu_online_cpu(int cpu) +{ + rcu_init_percpu_data(cpu, &rcu_state); + rcu_init_percpu_data(cpu, &rcu_bh_state); + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); +} + +/* + * Handle CPU online/offline notifcation events. + */ +static int __cpuinit rcu_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + long cpu = (long)hcpu; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + rcu_online_cpu(cpu); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + rcu_offline_cpu(cpu); + break; + default: + break; + } + return NOTIFY_OK; +} + +/* + * Compute the per-level fanout, either using the exact fanout specified + * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT. + */ +#ifdef CONFIG_RCU_FANOUT_EXACT +static void __init rcu_init_levelspread(struct rcu_state *rsp) +{ + int i; + + for (i = NUM_RCU_LVLS - 1; i >= 0; i--) + rsp->levelspread[i] = CONFIG_RCU_FANOUT; +} +#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */ +static void __init rcu_init_levelspread(struct rcu_state *rsp) +{ + int ccur; + int cprv; + int i; + + cprv = NR_CPUS; + for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + ccur = rsp->levelcnt[i]; + rsp->levelspread[i] = (cprv + ccur - 1) / ccur; + cprv = ccur; + } +} +#endif /* #else #ifdef CONFIG_RCU_FANOUT_EXACT */ + +/* + * Helper function for rcu_init() that initializes one rcu_state structure. + */ +static void __init rcu_init_one(struct rcu_state *rsp) +{ + int cpustride = 1; + int i; + int j; + struct rcu_node *rnp; + + /* Initialize the level-tracking arrays. */ + + for (i = 1; i < NUM_RCU_LVLS; i++) + rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1]; + rcu_init_levelspread(rsp); + + /* Initialize the elements themselves, starting from the leaves. */ + + for (i = NUM_RCU_LVLS - 1; i >= 0; i--) { + cpustride *= rsp->levelspread[i]; + rnp = rsp->level[i]; + for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) { + spin_lock_init(&rnp->lock); + rnp->qsmask = 0; + rnp->qsmaskinit = 0; + rnp->grplo = j * cpustride; + rnp->grphi = (j + 1) * cpustride - 1; + if (rnp->grphi >= NR_CPUS) + rnp->grphi = NR_CPUS - 1; + if (i == 0) { + rnp->grpnum = 0; + rnp->grpmask = 0; + rnp->parent = NULL; + } else { + rnp->grpnum = j % rsp->levelspread[i - 1]; + rnp->grpmask = 1UL << rnp->grpnum; + rnp->parent = rsp->level[i - 1] + + j / rsp->levelspread[i - 1]; + } + rnp->level = i; + } + } +} + +/* + * Helper macro for __rcu_init(). To be used nowhere else! + * Assigns leaf node pointers into each CPU's rcu_data structure. + */ +#define RCU_DATA_PTR_INIT(rsp, rcu_data) \ +do { \ + rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \ + j = 0; \ + for_each_possible_cpu(i) { \ + if (i > rnp[j].grphi) \ + j++; \ + per_cpu(rcu_data, i).mynode = &rnp[j]; \ + (rsp)->rda[i] = &per_cpu(rcu_data, i); \ + } \ +} while (0) + +static struct notifier_block __cpuinitdata rcu_nb = { + .notifier_call = rcu_cpu_notify, +}; + +void __init __rcu_init(void) +{ + int i; /* All used by RCU_DATA_PTR_INIT(). */ + int j; + struct rcu_node *rnp; + + printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n"); +#ifdef CONFIG_RCU_CPU_STALL_DETECTOR + printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n"); +#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */ + rcu_init_one(&rcu_state); + RCU_DATA_PTR_INIT(&rcu_state, rcu_data); + rcu_init_one(&rcu_bh_state); + RCU_DATA_PTR_INIT(&rcu_bh_state, rcu_bh_data); + + for_each_online_cpu(i) + rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i); + /* Register notifier for non-boot CPUs */ + register_cpu_notifier(&rcu_nb); + printk(KERN_WARNING "Experimental hierarchical RCU init done.\n"); +} + +module_param(blimit, int, 0); +module_param(qhimark, int, 0); +module_param(qlowmark, int, 0); diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c new file mode 100644 index 0000000..d6db3e83 --- /dev/null +++ b/kernel/rcutree_trace.c @@ -0,0 +1,271 @@ +/* + * Read-Copy Update tracing for classic implementation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright IBM Corporation, 2008 + * + * Papers: http://www.rdrop.com/users/paulmck/RCU + * + * For detailed explanation of Read-Copy Update mechanism see - + * Documentation/RCU + * + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/smp.h> +#include <linux/rcupdate.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <asm/atomic.h> +#include <linux/bitops.h> +#include <linux/module.h> +#include <linux/completion.h> +#include <linux/moduleparam.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/mutex.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) +{ + if (!rdp->beenonline) + return; + seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d rpfq=%ld rp=%x", + rdp->cpu, + cpu_is_offline(rdp->cpu) ? '!' : ' ', + rdp->completed, rdp->gpnum, + rdp->passed_quiesc, rdp->passed_quiesc_completed, + rdp->qs_pending, + rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending, + (int)(rdp->n_rcu_pending & 0xffff)); +#ifdef CONFIG_NO_HZ + seq_printf(m, " dt=%d/%d dn=%d df=%lu", + rdp->dynticks->dynticks, + rdp->dynticks->dynticks_nesting, + rdp->dynticks->dynticks_nmi, + rdp->dynticks_fqs); +#endif /* #ifdef CONFIG_NO_HZ */ + seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); + seq_printf(m, " ql=%ld b=%ld\n", rdp->qlen, rdp->blimit); +} + +#define PRINT_RCU_DATA(name, func, m) \ + do { \ + int _p_r_d_i; \ + \ + for_each_possible_cpu(_p_r_d_i) \ + func(m, &per_cpu(name, _p_r_d_i)); \ + } while (0) + +static int show_rcudata(struct seq_file *m, void *unused) +{ + seq_puts(m, "rcu:\n"); + PRINT_RCU_DATA(rcu_data, print_one_rcu_data, m); + seq_puts(m, "rcu_bh:\n"); + PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m); + return 0; +} + +static int rcudata_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcudata, NULL); +} + +static struct file_operations rcudata_fops = { + .owner = THIS_MODULE, + .open = rcudata_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) +{ + if (!rdp->beenonline) + return; + seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d,%ld,%ld", + rdp->cpu, + cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"", + rdp->completed, rdp->gpnum, + rdp->passed_quiesc, rdp->passed_quiesc_completed, + rdp->qs_pending, + rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending, + rdp->n_rcu_pending); +#ifdef CONFIG_NO_HZ + seq_printf(m, ",%d,%d,%d,%lu", + rdp->dynticks->dynticks, + rdp->dynticks->dynticks_nesting, + rdp->dynticks->dynticks_nmi, + rdp->dynticks_fqs); +#endif /* #ifdef CONFIG_NO_HZ */ + seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); + seq_printf(m, ",%ld,%ld\n", rdp->qlen, rdp->blimit); +} + +static int show_rcudata_csv(struct seq_file *m, void *unused) +{ + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",\"rpfq\",\"rp\","); +#ifdef CONFIG_NO_HZ + seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\","); +#endif /* #ifdef CONFIG_NO_HZ */ + seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n"); + seq_puts(m, "\"rcu:\"\n"); + PRINT_RCU_DATA(rcu_data, print_one_rcu_data_csv, m); + seq_puts(m, "\"rcu_bh:\"\n"); + PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m); + return 0; +} + +static int rcudata_csv_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcudata_csv, NULL); +} + +static struct file_operations rcudata_csv_fops = { + .owner = THIS_MODULE, + .open = rcudata_csv_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) +{ + int level = 0; + struct rcu_node *rnp; + + seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x " + "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n", + rsp->completed, rsp->gpnum, rsp->signaled, + (long)(rsp->jiffies_force_qs - jiffies), + (int)(jiffies & 0xffff), + rsp->n_force_qs, rsp->n_force_qs_ngp, + rsp->n_force_qs - rsp->n_force_qs_ngp, + rsp->n_force_qs_lh); + for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) { + if (rnp->level != level) { + seq_puts(m, "\n"); + level = rnp->level; + } + seq_printf(m, "%lx/%lx %d:%d ^%d ", + rnp->qsmask, rnp->qsmaskinit, + rnp->grplo, rnp->grphi, rnp->grpnum); + } + seq_puts(m, "\n"); +} + +static int show_rcuhier(struct seq_file *m, void *unused) +{ + seq_puts(m, "rcu:\n"); + print_one_rcu_state(m, &rcu_state); + seq_puts(m, "rcu_bh:\n"); + print_one_rcu_state(m, &rcu_bh_state); + return 0; +} + +static int rcuhier_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcuhier, NULL); +} + +static struct file_operations rcuhier_fops = { + .owner = THIS_MODULE, + .open = rcuhier_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int show_rcugp(struct seq_file *m, void *unused) +{ + seq_printf(m, "rcu: completed=%ld gpnum=%ld\n", + rcu_state.completed, rcu_state.gpnum); + seq_printf(m, "rcu_bh: completed=%ld gpnum=%ld\n", + rcu_bh_state.completed, rcu_bh_state.gpnum); + return 0; +} + +static int rcugp_open(struct inode *inode, struct file *file) +{ + return single_open(file, show_rcugp, NULL); +} + +static struct file_operations rcugp_fops = { + .owner = THIS_MODULE, + .open = rcugp_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir; +static int __init rcuclassic_trace_init(void) +{ + rcudir = debugfs_create_dir("rcu", NULL); + if (!rcudir) + goto out; + + datadir = debugfs_create_file("rcudata", 0444, rcudir, + NULL, &rcudata_fops); + if (!datadir) + goto free_out; + + datadir_csv = debugfs_create_file("rcudata.csv", 0444, rcudir, + NULL, &rcudata_csv_fops); + if (!datadir_csv) + goto free_out; + + gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops); + if (!gpdir) + goto free_out; + + hierdir = debugfs_create_file("rcuhier", 0444, rcudir, + NULL, &rcuhier_fops); + if (!hierdir) + goto free_out; + return 0; +free_out: + if (datadir) + debugfs_remove(datadir); + if (datadir_csv) + debugfs_remove(datadir_csv); + if (gpdir) + debugfs_remove(gpdir); + debugfs_remove(rcudir); +out: + return 1; +} + +static void __exit rcuclassic_trace_cleanup(void) +{ + debugfs_remove(datadir); + debugfs_remove(datadir_csv); + debugfs_remove(gpdir); + debugfs_remove(hierdir); + debugfs_remove(rcudir); +} + + +module_init(rcuclassic_trace_init); +module_exit(rcuclassic_trace_cleanup); + +MODULE_AUTHOR("Paul E. McKenney"); +MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation"); +MODULE_LICENSE("GPL"); diff --git a/kernel/res_counter.c b/kernel/res_counter.c index f275c8e..bf8e753 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -15,10 +15,11 @@ #include <linux/uaccess.h> #include <linux/mm.h> -void res_counter_init(struct res_counter *counter) +void res_counter_init(struct res_counter *counter, struct res_counter *parent) { spin_lock_init(&counter->lock); counter->limit = (unsigned long long)LLONG_MAX; + counter->parent = parent; } int res_counter_charge_locked(struct res_counter *counter, unsigned long val) @@ -34,14 +35,34 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val) return 0; } -int res_counter_charge(struct res_counter *counter, unsigned long val) +int res_counter_charge(struct res_counter *counter, unsigned long val, + struct res_counter **limit_fail_at) { int ret; unsigned long flags; - - spin_lock_irqsave(&counter->lock, flags); - ret = res_counter_charge_locked(counter, val); - spin_unlock_irqrestore(&counter->lock, flags); + struct res_counter *c, *u; + + *limit_fail_at = NULL; + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + ret = res_counter_charge_locked(c, val); + spin_unlock(&c->lock); + if (ret < 0) { + *limit_fail_at = c; + goto undo; + } + } + ret = 0; + goto done; +undo: + for (u = counter; u != c; u = u->parent) { + spin_lock(&u->lock); + res_counter_uncharge_locked(u, val); + spin_unlock(&u->lock); + } +done: + local_irq_restore(flags); return ret; } @@ -56,10 +77,15 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) void res_counter_uncharge(struct res_counter *counter, unsigned long val) { unsigned long flags; + struct res_counter *c; - spin_lock_irqsave(&counter->lock, flags); - res_counter_uncharge_locked(counter, val); - spin_unlock_irqrestore(&counter->lock, flags); + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + res_counter_uncharge_locked(c, val); + spin_unlock(&c->lock); + } + local_irq_restore(flags); } diff --git a/kernel/resource.c b/kernel/resource.c index 4337063..ca6a153 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -623,7 +623,7 @@ resource_size_t resource_alignment(struct resource *res) */ struct resource * __request_region(struct resource *parent, resource_size_t start, resource_size_t n, - const char *name) + const char *name, int flags) { struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL); @@ -634,6 +634,7 @@ struct resource * __request_region(struct resource *parent, res->start = start; res->end = start + n - 1; res->flags = IORESOURCE_BUSY; + res->flags |= flags; write_lock(&resource_lock); @@ -679,7 +680,7 @@ int __check_region(struct resource *parent, resource_size_t start, { struct resource * res; - res = __request_region(parent, start, n, "check-region"); + res = __request_region(parent, start, n, "check-region", 0); if (!res) return -EBUSY; @@ -776,7 +777,7 @@ struct resource * __devm_request_region(struct device *dev, dr->start = start; dr->n = n; - res = __request_region(parent, start, n, name); + res = __request_region(parent, start, n, name, 0); if (res) devres_add(dev, dr); else @@ -853,6 +854,15 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size) if (PFN_DOWN(p->start) <= PFN_DOWN(addr) && PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1)) continue; + /* + * if a resource is "BUSY", it's not a hardware resource + * but a driver mapping of such a resource; we don't want + * to warn for those; some drivers legitimately map only + * partial hardware resources. (example: vesafb) + */ + if (p->flags & IORESOURCE_BUSY) + continue; + printk(KERN_WARNING "resource map sanity check conflict: " "0x%llx 0x%llx 0x%llx 0x%llx %s\n", (unsigned long long)addr, @@ -867,3 +877,57 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size) return err; } + +#ifdef CONFIG_STRICT_DEVMEM +static int strict_iomem_checks = 1; +#else +static int strict_iomem_checks; +#endif + +/* + * check if an address is reserved in the iomem resource tree + * returns 1 if reserved, 0 if not reserved. + */ +int iomem_is_exclusive(u64 addr) +{ + struct resource *p = &iomem_resource; + int err = 0; + loff_t l; + int size = PAGE_SIZE; + + if (!strict_iomem_checks) + return 0; + + addr = addr & PAGE_MASK; + + read_lock(&resource_lock); + for (p = p->child; p ; p = r_next(NULL, p, &l)) { + /* + * We can probably skip the resources without + * IORESOURCE_IO attribute? + */ + if (p->start >= addr + size) + break; + if (p->end < addr) + continue; + if (p->flags & IORESOURCE_BUSY && + p->flags & IORESOURCE_EXCLUSIVE) { + err = 1; + break; + } + } + read_unlock(&resource_lock); + + return err; +} + +static int __init strict_iomem(char *str) +{ + if (strstr(str, "relaxed")) + strict_iomem_checks = 0; + if (strstr(str, "strict")) + strict_iomem_checks = 1; + return 1; +} + +__setup("iomem=", strict_iomem); diff --git a/kernel/sched.c b/kernel/sched.c index e4bb1dd..deb5ac8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -118,6 +118,12 @@ */ #define RUNTIME_INF ((u64)~0ULL) +DEFINE_TRACE(sched_wait_task); +DEFINE_TRACE(sched_wakeup); +DEFINE_TRACE(sched_wakeup_new); +DEFINE_TRACE(sched_switch); +DEFINE_TRACE(sched_migrate_task); + #ifdef CONFIG_SMP /* * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) @@ -203,7 +209,6 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); rt_b->rt_period_timer.function = sched_rt_period_timer; - rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED; } static inline int rt_bandwidth_enabled(void) @@ -261,6 +266,10 @@ struct task_group { struct cgroup_subsys_state css; #endif +#ifdef CONFIG_USER_SCHED + uid_t uid; +#endif + #ifdef CONFIG_FAIR_GROUP_SCHED /* schedulable entities of this group on each cpu */ struct sched_entity **se; @@ -286,6 +295,12 @@ struct task_group { #ifdef CONFIG_USER_SCHED +/* Helper function to pass uid information to create_sched_user() */ +void set_tg_uid(struct user_struct *user) +{ + user->tg->uid = user->uid; +} + /* * Root task group. * Every UID task group (including init_task_group aka UID-0) will @@ -345,7 +360,9 @@ static inline struct task_group *task_group(struct task_struct *p) struct task_group *tg; #ifdef CONFIG_USER_SCHED - tg = p->user->tg; + rcu_read_lock(); + tg = __task_cred(p)->user->tg; + rcu_read_unlock(); #elif defined(CONFIG_CGROUP_SCHED) tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), struct task_group, css); @@ -481,18 +498,26 @@ struct rt_rq { */ struct root_domain { atomic_t refcount; - cpumask_t span; - cpumask_t online; + cpumask_var_t span; + cpumask_var_t online; /* * The "RT overload" flag: it gets set if a CPU has more than * one runnable RT task. */ - cpumask_t rto_mask; + cpumask_var_t rto_mask; atomic_t rto_count; #ifdef CONFIG_SMP struct cpupri cpupri; #endif +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) + /* + * Preferred wake up cpu nominated by sched_mc balance that will be + * used when most cpus are idle in the system indicating overall very + * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2) + */ + unsigned int sched_mc_preferred_wakeup_cpu; +#endif }; /* @@ -586,6 +611,8 @@ struct rq { #ifdef CONFIG_SCHEDSTATS /* latency stats */ struct sched_info rq_sched_info; + unsigned long long rq_cpu_time; + /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ /* sys_sched_yield() stats */ unsigned int yld_exp_empty; @@ -703,45 +730,18 @@ static __read_mostly char *sched_feat_names[] = { #undef SCHED_FEAT -static int sched_feat_open(struct inode *inode, struct file *filp) +static int sched_feat_show(struct seq_file *m, void *v) { - filp->private_data = inode->i_private; - return 0; -} - -static ssize_t -sched_feat_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char *buf; - int r = 0; - int len = 0; int i; for (i = 0; sched_feat_names[i]; i++) { - len += strlen(sched_feat_names[i]); - len += 4; - } - - buf = kmalloc(len + 2, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - for (i = 0; sched_feat_names[i]; i++) { - if (sysctl_sched_features & (1UL << i)) - r += sprintf(buf + r, "%s ", sched_feat_names[i]); - else - r += sprintf(buf + r, "NO_%s ", sched_feat_names[i]); + if (!(sysctl_sched_features & (1UL << i))) + seq_puts(m, "NO_"); + seq_printf(m, "%s ", sched_feat_names[i]); } + seq_puts(m, "\n"); - r += sprintf(buf + r, "\n"); - WARN_ON(r >= len + 2); - - r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); - - kfree(buf); - - return r; + return 0; } static ssize_t @@ -786,10 +786,17 @@ sched_feat_write(struct file *filp, const char __user *ubuf, return cnt; } +static int sched_feat_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_feat_show, NULL); +} + static struct file_operations sched_feat_fops = { - .open = sched_feat_open, - .read = sched_feat_read, - .write = sched_feat_write, + .open = sched_feat_open, + .write = sched_feat_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, }; static __init int sched_init_debug(void) @@ -1139,7 +1146,6 @@ static void init_rq_hrtick(struct rq *rq) hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); rq->hrtick_timer.function = hrtick; - rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; } #else /* CONFIG_SCHED_HRTICK */ static inline void hrtick_clear(struct rq *rq) @@ -1474,27 +1480,13 @@ static void update_group_shares_cpu(struct task_group *tg, int cpu, unsigned long sd_shares, unsigned long sd_rq_weight) { - int boost = 0; unsigned long shares; unsigned long rq_weight; if (!tg->se[cpu]) return; - rq_weight = tg->cfs_rq[cpu]->load.weight; - - /* - * If there are currently no tasks on the cpu pretend there is one of - * average load so that when a new task gets to run here it will not - * get delayed by group starvation. - */ - if (!rq_weight) { - boost = 1; - rq_weight = NICE_0_LOAD; - } - - if (unlikely(rq_weight > sd_rq_weight)) - rq_weight = sd_rq_weight; + rq_weight = tg->cfs_rq[cpu]->rq_weight; /* * \Sum shares * rq_weight @@ -1502,7 +1494,7 @@ update_group_shares_cpu(struct task_group *tg, int cpu, * \Sum rq_weight * */ - shares = (sd_shares * rq_weight) / (sd_rq_weight + 1); + shares = (sd_shares * rq_weight) / sd_rq_weight; shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES); if (abs(shares - tg->se[cpu]->load.weight) > @@ -1511,11 +1503,7 @@ update_group_shares_cpu(struct task_group *tg, int cpu, unsigned long flags; spin_lock_irqsave(&rq->lock, flags); - /* - * record the actual number of shares, not the boosted amount. - */ - tg->cfs_rq[cpu]->shares = boost ? 0 : shares; - tg->cfs_rq[cpu]->rq_weight = rq_weight; + tg->cfs_rq[cpu]->shares = shares; __set_se_shares(tg->se[cpu], shares); spin_unlock_irqrestore(&rq->lock, flags); @@ -1529,13 +1517,23 @@ update_group_shares_cpu(struct task_group *tg, int cpu, */ static int tg_shares_up(struct task_group *tg, void *data) { - unsigned long rq_weight = 0; + unsigned long weight, rq_weight = 0; unsigned long shares = 0; struct sched_domain *sd = data; int i; - for_each_cpu_mask(i, sd->span) { - rq_weight += tg->cfs_rq[i]->load.weight; + for_each_cpu(i, sched_domain_span(sd)) { + /* + * If there are currently no tasks on the cpu pretend there + * is one of average load so that when a new task gets to + * run here it will not get delayed by group starvation. + */ + weight = tg->cfs_rq[i]->load.weight; + if (!weight) + weight = NICE_0_LOAD; + + tg->cfs_rq[i]->rq_weight = weight; + rq_weight += weight; shares += tg->cfs_rq[i]->shares; } @@ -1545,10 +1543,7 @@ static int tg_shares_up(struct task_group *tg, void *data) if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE)) shares = tg->shares; - if (!rq_weight) - rq_weight = cpus_weight(sd->span) * NICE_0_LOAD; - - for_each_cpu_mask(i, sd->span) + for_each_cpu(i, sched_domain_span(sd)) update_group_shares_cpu(tg, i, shares, rq_weight); return 0; @@ -1612,6 +1607,39 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) #endif +/* + * double_lock_balance - lock the busiest runqueue, this_rq is locked already. + */ +static int double_lock_balance(struct rq *this_rq, struct rq *busiest) + __releases(this_rq->lock) + __acquires(busiest->lock) + __acquires(this_rq->lock) +{ + int ret = 0; + + if (unlikely(!irqs_disabled())) { + /* printk() doesn't work good under rq->lock */ + spin_unlock(&this_rq->lock); + BUG_ON(1); + } + if (unlikely(!spin_trylock(&busiest->lock))) { + if (busiest < this_rq) { + spin_unlock(&this_rq->lock); + spin_lock(&busiest->lock); + spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); + ret = 1; + } else + spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); + } + return ret; +} + +static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) + __releases(busiest->lock) +{ + spin_unlock(&busiest->lock); + lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); +} #endif #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1845,6 +1873,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) clock_offset = old_rq->clock - new_rq->clock; + trace_sched_migrate_task(p, task_cpu(p), new_cpu); + #ifdef CONFIG_SCHEDSTATS if (p->se.wait_start) p->se.wait_start -= clock_offset; @@ -2079,15 +2109,17 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) int i; /* Skip over this group if it has no CPUs allowed */ - if (!cpus_intersects(group->cpumask, p->cpus_allowed)) + if (!cpumask_intersects(sched_group_cpus(group), + &p->cpus_allowed)) continue; - local_group = cpu_isset(this_cpu, group->cpumask); + local_group = cpumask_test_cpu(this_cpu, + sched_group_cpus(group)); /* Tally up the load of all CPUs in the group */ avg_load = 0; - for_each_cpu_mask_nr(i, group->cpumask) { + for_each_cpu(i, sched_group_cpus(group)) { /* Bias balancing toward cpus of our domain */ if (local_group) load = source_load(i, load_idx); @@ -2119,17 +2151,14 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) * find_idlest_cpu - find the idlest cpu among the cpus in group. */ static int -find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu, - cpumask_t *tmp) +find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) { unsigned long load, min_load = ULONG_MAX; int idlest = -1; int i; /* Traverse only the allowed CPUs */ - cpus_and(*tmp, group->cpumask, p->cpus_allowed); - - for_each_cpu_mask_nr(i, *tmp) { + for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { load = weighted_cpuload(i); if (load < min_load || (load == min_load && i == this_cpu)) { @@ -2171,7 +2200,6 @@ static int sched_balance_self(int cpu, int flag) update_shares(sd); while (sd) { - cpumask_t span, tmpmask; struct sched_group *group; int new_cpu, weight; @@ -2180,14 +2208,13 @@ static int sched_balance_self(int cpu, int flag) continue; } - span = sd->span; group = find_idlest_group(sd, t, cpu); if (!group) { sd = sd->child; continue; } - new_cpu = find_idlest_cpu(group, t, cpu, &tmpmask); + new_cpu = find_idlest_cpu(group, t, cpu); if (new_cpu == -1 || new_cpu == cpu) { /* Now try balancing at a lower domain level of cpu */ sd = sd->child; @@ -2196,10 +2223,10 @@ static int sched_balance_self(int cpu, int flag) /* Now try balancing at a lower domain level of new_cpu */ cpu = new_cpu; + weight = cpumask_weight(sched_domain_span(sd)); sd = NULL; - weight = cpus_weight(span); for_each_domain(cpu, tmp) { - if (weight <= cpus_weight(tmp->span)) + if (weight <= cpumask_weight(sched_domain_span(tmp))) break; if (tmp->flags & flag) sd = tmp; @@ -2244,7 +2271,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) cpu = task_cpu(p); for_each_domain(this_cpu, sd) { - if (cpu_isset(cpu, sd->span)) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { update_shares(sd); break; } @@ -2254,6 +2281,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) smp_wmb(); rq = task_rq_lock(p, &flags); + update_rq_clock(rq); old_state = p->state; if (!(old_state & state)) goto out; @@ -2292,7 +2320,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) else { struct sched_domain *sd; for_each_domain(this_cpu, sd) { - if (cpu_isset(cpu, sd->span)) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { schedstat_inc(sd, ttwu_wake_remote); break; } @@ -2311,12 +2339,11 @@ out_activate: schedstat_inc(p, se.nr_wakeups_local); else schedstat_inc(p, se.nr_wakeups_remote); - update_rq_clock(rq); activate_task(rq, p, 1); success = 1; out_running: - trace_sched_wakeup(rq, p); + trace_sched_wakeup(rq, p, success); check_preempt_curr(rq, p, sync); p->state = TASK_RUNNING; @@ -2449,7 +2476,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) p->sched_class->task_new(rq, p); inc_nr_running(rq); } - trace_sched_wakeup_new(rq, p); + trace_sched_wakeup_new(rq, p, 1); check_preempt_curr(rq, p, 0); #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) @@ -2812,40 +2839,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2) } /* - * double_lock_balance - lock the busiest runqueue, this_rq is locked already. - */ -static int double_lock_balance(struct rq *this_rq, struct rq *busiest) - __releases(this_rq->lock) - __acquires(busiest->lock) - __acquires(this_rq->lock) -{ - int ret = 0; - - if (unlikely(!irqs_disabled())) { - /* printk() doesn't work good under rq->lock */ - spin_unlock(&this_rq->lock); - BUG_ON(1); - } - if (unlikely(!spin_trylock(&busiest->lock))) { - if (busiest < this_rq) { - spin_unlock(&this_rq->lock); - spin_lock(&busiest->lock); - spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); - ret = 1; - } else - spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); - } - return ret; -} - -static void double_unlock_balance(struct rq *this_rq, struct rq *busiest) - __releases(busiest->lock) -{ - spin_unlock(&busiest->lock); - lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); -} - -/* * If dest_cpu is allowed for this process, migrate the task to it. * This is accomplished by forcing the cpu_allowed mask to only * allow dest_cpu, which will force the cpu onto dest_cpu. Then @@ -2858,11 +2851,10 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu) struct rq *rq; rq = task_rq_lock(p, &flags); - if (!cpu_isset(dest_cpu, p->cpus_allowed) + if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed) || unlikely(!cpu_active(dest_cpu))) goto out; - trace_sched_migrate_task(rq, p, dest_cpu); /* force the process onto the specified CPU */ if (migrate_task(p, dest_cpu, &req)) { /* Need to wait for migration thread (might exit: take ref). */ @@ -2924,7 +2916,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 2) cannot be migrated to this CPU due to cpus_allowed, or * 3) are cache-hot on their current CPU. */ - if (!cpu_isset(this_cpu, p->cpus_allowed)) { + if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) { schedstat_inc(p, se.nr_failed_migrations_affine); return 0; } @@ -3099,7 +3091,7 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, static struct sched_group * find_busiest_group(struct sched_domain *sd, int this_cpu, unsigned long *imbalance, enum cpu_idle_type idle, - int *sd_idle, const cpumask_t *cpus, int *balance) + int *sd_idle, const struct cpumask *cpus, int *balance) { struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups; unsigned long max_load, avg_load, total_load, this_load, total_pwr; @@ -3135,10 +3127,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, unsigned long sum_avg_load_per_task; unsigned long avg_load_per_task; - local_group = cpu_isset(this_cpu, group->cpumask); + local_group = cpumask_test_cpu(this_cpu, + sched_group_cpus(group)); if (local_group) - balance_cpu = first_cpu(group->cpumask); + balance_cpu = cpumask_first(sched_group_cpus(group)); /* Tally up the load of all CPUs in the group */ sum_weighted_load = sum_nr_running = avg_load = 0; @@ -3147,13 +3140,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, max_cpu_load = 0; min_cpu_load = ~0UL; - for_each_cpu_mask_nr(i, group->cpumask) { - struct rq *rq; - - if (!cpu_isset(i, *cpus)) - continue; - - rq = cpu_rq(i); + for_each_cpu_and(i, sched_group_cpus(group), cpus) { + struct rq *rq = cpu_rq(i); if (*sd_idle && rq->nr_running) *sd_idle = 0; @@ -3264,8 +3252,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, */ if ((sum_nr_running < min_nr_running) || (sum_nr_running == min_nr_running && - first_cpu(group->cpumask) < - first_cpu(group_min->cpumask))) { + cpumask_first(sched_group_cpus(group)) > + cpumask_first(sched_group_cpus(group_min)))) { group_min = group; min_nr_running = sum_nr_running; min_load_per_task = sum_weighted_load / @@ -3280,8 +3268,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, if (sum_nr_running <= group_capacity - 1) { if (sum_nr_running > leader_nr_running || (sum_nr_running == leader_nr_running && - first_cpu(group->cpumask) > - first_cpu(group_leader->cpumask))) { + cpumask_first(sched_group_cpus(group)) < + cpumask_first(sched_group_cpus(group_leader)))) { group_leader = group; leader_nr_running = sum_nr_running; } @@ -3407,6 +3395,10 @@ out_balanced: if (this == group_leader && group_leader != group_min) { *imbalance = min_load_per_task; + if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) { + cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu = + cpumask_first(sched_group_cpus(group_leader)); + } return group_min; } #endif @@ -3420,16 +3412,16 @@ ret: */ static struct rq * find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, - unsigned long imbalance, const cpumask_t *cpus) + unsigned long imbalance, const struct cpumask *cpus) { struct rq *busiest = NULL, *rq; unsigned long max_load = 0; int i; - for_each_cpu_mask_nr(i, group->cpumask) { + for_each_cpu(i, sched_group_cpus(group)) { unsigned long wl; - if (!cpu_isset(i, *cpus)) + if (!cpumask_test_cpu(i, cpus)) continue; rq = cpu_rq(i); @@ -3459,7 +3451,7 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, */ static int load_balance(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, - int *balance, cpumask_t *cpus) + int *balance, struct cpumask *cpus) { int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0; struct sched_group *group; @@ -3467,7 +3459,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, struct rq *busiest; unsigned long flags; - cpus_setall(*cpus); + cpumask_setall(cpus); /* * When power savings policy is enabled for the parent domain, idle @@ -3527,8 +3519,8 @@ redo: /* All tasks on this runqueue were pinned by CPU affinity */ if (unlikely(all_pinned)) { - cpu_clear(cpu_of(busiest), *cpus); - if (!cpus_empty(*cpus)) + cpumask_clear_cpu(cpu_of(busiest), cpus); + if (!cpumask_empty(cpus)) goto redo; goto out_balanced; } @@ -3545,7 +3537,8 @@ redo: /* don't kick the migration_thread, if the curr * task on busiest cpu can't be moved to this_cpu */ - if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) { + if (!cpumask_test_cpu(this_cpu, + &busiest->curr->cpus_allowed)) { spin_unlock_irqrestore(&busiest->lock, flags); all_pinned = 1; goto out_one_pinned; @@ -3620,7 +3613,7 @@ out: */ static int load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, - cpumask_t *cpus) + struct cpumask *cpus) { struct sched_group *group; struct rq *busiest = NULL; @@ -3629,7 +3622,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, int sd_idle = 0; int all_pinned = 0; - cpus_setall(*cpus); + cpumask_setall(cpus); /* * When power savings policy is enabled for the parent domain, idle @@ -3673,17 +3666,76 @@ redo: double_unlock_balance(this_rq, busiest); if (unlikely(all_pinned)) { - cpu_clear(cpu_of(busiest), *cpus); - if (!cpus_empty(*cpus)) + cpumask_clear_cpu(cpu_of(busiest), cpus); + if (!cpumask_empty(cpus)) goto redo; } } if (!ld_moved) { + int active_balance = 0; + schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]); if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) return -1; + + if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) + return -1; + + if (sd->nr_balance_failed++ < 2) + return -1; + + /* + * The only task running in a non-idle cpu can be moved to this + * cpu in an attempt to completely freeup the other CPU + * package. The same method used to move task in load_balance() + * have been extended for load_balance_newidle() to speedup + * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2) + * + * The package power saving logic comes from + * find_busiest_group(). If there are no imbalance, then + * f_b_g() will return NULL. However when sched_mc={1,2} then + * f_b_g() will select a group from which a running task may be + * pulled to this cpu in order to make the other package idle. + * If there is no opportunity to make a package idle and if + * there are no imbalance, then f_b_g() will return NULL and no + * action will be taken in load_balance_newidle(). + * + * Under normal task pull operation due to imbalance, there + * will be more than one task in the source run queue and + * move_tasks() will succeed. ld_moved will be true and this + * active balance code will not be triggered. + */ + + /* Lock busiest in correct order while this_rq is held */ + double_lock_balance(this_rq, busiest); + + /* + * don't kick the migration_thread, if the curr + * task on busiest cpu can't be moved to this_cpu + */ + if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { + double_unlock_balance(this_rq, busiest); + all_pinned = 1; + return ld_moved; + } + + if (!busiest->active_balance) { + busiest->active_balance = 1; + busiest->push_cpu = this_cpu; + active_balance = 1; + } + + double_unlock_balance(this_rq, busiest); + /* + * Should not call ttwu while holding a rq->lock + */ + spin_unlock(&this_rq->lock); + if (active_balance) + wake_up_process(busiest->migration_thread); + spin_lock(&this_rq->lock); + } else sd->nr_balance_failed = 0; @@ -3707,9 +3759,12 @@ out_balanced: static void idle_balance(int this_cpu, struct rq *this_rq) { struct sched_domain *sd; - int pulled_task = -1; + int pulled_task = 0; unsigned long next_balance = jiffies + HZ; - cpumask_t tmpmask; + cpumask_var_t tmpmask; + + if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC)) + return; for_each_domain(this_cpu, sd) { unsigned long interval; @@ -3720,7 +3775,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) if (sd->flags & SD_BALANCE_NEWIDLE) /* If we've pulled tasks over stop searching: */ pulled_task = load_balance_newidle(this_cpu, this_rq, - sd, &tmpmask); + sd, tmpmask); interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) @@ -3735,6 +3790,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) */ this_rq->next_balance = next_balance; } + free_cpumask_var(tmpmask); } /* @@ -3772,7 +3828,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) /* Search for an sd spanning us and the target CPU. */ for_each_domain(target_cpu, sd) { if ((sd->flags & SD_LOAD_BALANCE) && - cpu_isset(busiest_cpu, sd->span)) + cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) break; } @@ -3791,10 +3847,9 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) #ifdef CONFIG_NO_HZ static struct { atomic_t load_balancer; - cpumask_t cpu_mask; + cpumask_var_t cpu_mask; } nohz ____cacheline_aligned = { .load_balancer = ATOMIC_INIT(-1), - .cpu_mask = CPU_MASK_NONE, }; /* @@ -3822,7 +3877,7 @@ int select_nohz_load_balancer(int stop_tick) int cpu = smp_processor_id(); if (stop_tick) { - cpu_set(cpu, nohz.cpu_mask); + cpumask_set_cpu(cpu, nohz.cpu_mask); cpu_rq(cpu)->in_nohz_recently = 1; /* @@ -3836,7 +3891,7 @@ int select_nohz_load_balancer(int stop_tick) } /* time for ilb owner also to sleep */ - if (cpus_weight(nohz.cpu_mask) == num_online_cpus()) { + if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { if (atomic_read(&nohz.load_balancer) == cpu) atomic_set(&nohz.load_balancer, -1); return 0; @@ -3849,10 +3904,10 @@ int select_nohz_load_balancer(int stop_tick) } else if (atomic_read(&nohz.load_balancer) == cpu) return 1; } else { - if (!cpu_isset(cpu, nohz.cpu_mask)) + if (!cpumask_test_cpu(cpu, nohz.cpu_mask)) return 0; - cpu_clear(cpu, nohz.cpu_mask); + cpumask_clear_cpu(cpu, nohz.cpu_mask); if (atomic_read(&nohz.load_balancer) == cpu) if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) @@ -3880,7 +3935,11 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; int need_serialize; - cpumask_t tmp; + cpumask_var_t tmp; + + /* Fails alloc? Rebalancing probably not a priority right now. */ + if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) + return; for_each_domain(cpu, sd) { if (!(sd->flags & SD_LOAD_BALANCE)) @@ -3905,7 +3964,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) } if (time_after_eq(jiffies, sd->last_balance + interval)) { - if (load_balance(cpu, rq, sd, idle, &balance, &tmp)) { + if (load_balance(cpu, rq, sd, idle, &balance, tmp)) { /* * We've pulled tasks over so either we're no * longer idle, or one of our SMT siblings is @@ -3939,6 +3998,8 @@ out: */ if (likely(update_next_balance)) rq->next_balance = next_balance; + + free_cpumask_var(tmp); } /* @@ -3963,12 +4024,13 @@ static void run_rebalance_domains(struct softirq_action *h) */ if (this_rq->idle_at_tick && atomic_read(&nohz.load_balancer) == this_cpu) { - cpumask_t cpus = nohz.cpu_mask; struct rq *rq; int balance_cpu; - cpu_clear(this_cpu, cpus); - for_each_cpu_mask_nr(balance_cpu, cpus) { + for_each_cpu(balance_cpu, nohz.cpu_mask) { + if (balance_cpu == this_cpu) + continue; + /* * If this cpu gets work to do, stop the load balancing * work being done for other cpus. Next load @@ -4006,7 +4068,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu) rq->in_nohz_recently = 0; if (atomic_read(&nohz.load_balancer) == cpu) { - cpu_clear(cpu, nohz.cpu_mask); + cpumask_clear_cpu(cpu, nohz.cpu_mask); atomic_set(&nohz.load_balancer, -1); } @@ -4019,7 +4081,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu) * TBD: Traverse the sched domains and nominate * the nearest cpu in the nohz.cpu_mask. */ - int ilb = first_cpu(nohz.cpu_mask); + int ilb = cpumask_first(nohz.cpu_mask); if (ilb < nr_cpu_ids) resched_cpu(ilb); @@ -4031,7 +4093,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu) * cpus with ticks stopped, is it time for that to stop? */ if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && - cpus_weight(nohz.cpu_mask) == num_online_cpus()) { + cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { resched_cpu(cpu); return; } @@ -4041,7 +4103,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu) * someone else, then no need raise the SCHED_SOFTIRQ */ if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && - cpu_isset(cpu, nohz.cpu_mask)) + cpumask_test_cpu(cpu, nohz.cpu_mask)) return; #endif if (time_after_eq(jiffies, rq->next_balance)) @@ -4093,13 +4155,17 @@ unsigned long long task_delta_exec(struct task_struct *p) * Account user cpu time to a process. * @p: the process that the cpu time gets accounted to * @cputime: the cpu time spent in user space since the last update + * @cputime_scaled: cputime scaled by cpu frequency */ -void account_user_time(struct task_struct *p, cputime_t cputime) +void account_user_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; cputime64_t tmp; + /* Add user time to process. */ p->utime = cputime_add(p->utime, cputime); + p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); account_group_user_time(p, cputime); /* Add user time to cpustat. */ @@ -4116,51 +4182,48 @@ void account_user_time(struct task_struct *p, cputime_t cputime) * Account guest cpu time to a process. * @p: the process that the cpu time gets accounted to * @cputime: the cpu time spent in virtual machine since the last update + * @cputime_scaled: cputime scaled by cpu frequency */ -static void account_guest_time(struct task_struct *p, cputime_t cputime) +static void account_guest_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) { cputime64_t tmp; struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; tmp = cputime_to_cputime64(cputime); + /* Add guest time to process. */ p->utime = cputime_add(p->utime, cputime); + p->utimescaled = cputime_add(p->utimescaled, cputime_scaled); account_group_user_time(p, cputime); p->gtime = cputime_add(p->gtime, cputime); + /* Add guest time to cpustat. */ cpustat->user = cputime64_add(cpustat->user, tmp); cpustat->guest = cputime64_add(cpustat->guest, tmp); } /* - * Account scaled user cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in user space since the last update - */ -void account_user_time_scaled(struct task_struct *p, cputime_t cputime) -{ - p->utimescaled = cputime_add(p->utimescaled, cputime); -} - -/* * Account system cpu time to a process. * @p: the process that the cpu time gets accounted to * @hardirq_offset: the offset to subtract from hardirq_count() * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency */ void account_system_time(struct task_struct *p, int hardirq_offset, - cputime_t cputime) + cputime_t cputime, cputime_t cputime_scaled) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - struct rq *rq = this_rq(); cputime64_t tmp; if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { - account_guest_time(p, cputime); + account_guest_time(p, cputime, cputime_scaled); return; } + /* Add system time to process. */ p->stime = cputime_add(p->stime, cputime); + p->stimescaled = cputime_add(p->stimescaled, cputime_scaled); account_group_system_time(p, cputime); /* Add system time to cpustat. */ @@ -4169,50 +4232,85 @@ void account_system_time(struct task_struct *p, int hardirq_offset, cpustat->irq = cputime64_add(cpustat->irq, tmp); else if (softirq_count()) cpustat->softirq = cputime64_add(cpustat->softirq, tmp); - else if (p != rq->idle) - cpustat->system = cputime64_add(cpustat->system, tmp); - else if (atomic_read(&rq->nr_iowait) > 0) - cpustat->iowait = cputime64_add(cpustat->iowait, tmp); else - cpustat->idle = cputime64_add(cpustat->idle, tmp); + cpustat->system = cputime64_add(cpustat->system, tmp); + /* Account for system time used */ acct_update_integrals(p); } /* - * Account scaled system cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @hardirq_offset: the offset to subtract from hardirq_count() - * @cputime: the cpu time spent in kernel space since the last update + * Account for involuntary wait time. + * @steal: the cpu time spent in involuntary wait */ -void account_system_time_scaled(struct task_struct *p, cputime_t cputime) +void account_steal_time(cputime_t cputime) { - p->stimescaled = cputime_add(p->stimescaled, cputime); + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + cputime64_t cputime64 = cputime_to_cputime64(cputime); + + cpustat->steal = cputime64_add(cpustat->steal, cputime64); } /* - * Account for involuntary wait time. - * @p: the process from which the cpu time has been stolen - * @steal: the cpu time spent in involuntary wait + * Account for idle time. + * @cputime: the cpu time spent in idle wait */ -void account_steal_time(struct task_struct *p, cputime_t steal) +void account_idle_time(cputime_t cputime) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; - cputime64_t tmp = cputime_to_cputime64(steal); + cputime64_t cputime64 = cputime_to_cputime64(cputime); struct rq *rq = this_rq(); - if (p == rq->idle) { - p->stime = cputime_add(p->stime, steal); - account_group_system_time(p, steal); - if (atomic_read(&rq->nr_iowait) > 0) - cpustat->iowait = cputime64_add(cpustat->iowait, tmp); - else - cpustat->idle = cputime64_add(cpustat->idle, tmp); - } else - cpustat->steal = cputime64_add(cpustat->steal, tmp); + if (atomic_read(&rq->nr_iowait) > 0) + cpustat->iowait = cputime64_add(cpustat->iowait, cputime64); + else + cpustat->idle = cputime64_add(cpustat->idle, cputime64); +} + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + +/* + * Account a single tick of cpu time. + * @p: the process that the cpu time gets accounted to + * @user_tick: indicates if the tick is a user or a system tick + */ +void account_process_tick(struct task_struct *p, int user_tick) +{ + cputime_t one_jiffy = jiffies_to_cputime(1); + cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy); + struct rq *rq = this_rq(); + + if (user_tick) + account_user_time(p, one_jiffy, one_jiffy_scaled); + else if (p != rq->idle) + account_system_time(p, HARDIRQ_OFFSET, one_jiffy, + one_jiffy_scaled); + else + account_idle_time(one_jiffy); +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); } /* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + account_idle_time(jiffies_to_cputime(ticks)); +} + +#endif + +/* * Use precise platform statistics if available: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING @@ -4339,7 +4437,7 @@ void __kprobes sub_preempt_count(int val) /* * Underflow? */ - if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked()))) return; /* * Is the spinlock portion underflowing? @@ -5134,6 +5232,22 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) set_load_weight(p); } +/* + * check the target process has a UID that matches the current process's + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + bool match; + + rcu_read_lock(); + pcred = __task_cred(p); + match = (cred->euid == pcred->euid || + cred->euid == pcred->uid); + rcu_read_unlock(); + return match; +} + static int __sched_setscheduler(struct task_struct *p, int policy, struct sched_param *param, bool user) { @@ -5193,8 +5307,7 @@ recheck: return -EPERM; /* can't change other user's priorities */ - if ((current->euid != p->euid) && - (current->euid != p->uid)) + if (!check_same_owner(p)) return -EPERM; } @@ -5400,10 +5513,9 @@ out_unlock: return retval; } -long sched_setaffinity(pid_t pid, const cpumask_t *in_mask) +long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) { - cpumask_t cpus_allowed; - cpumask_t new_mask = *in_mask; + cpumask_var_t cpus_allowed, new_mask; struct task_struct *p; int retval; @@ -5425,46 +5537,57 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask) get_task_struct(p); read_unlock(&tasklist_lock); + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_put_task; + } + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_free_cpus_allowed; + } retval = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_NICE)) + if (!check_same_owner(p) && !capable(CAP_SYS_NICE)) goto out_unlock; retval = security_task_setscheduler(p, 0, NULL); if (retval) goto out_unlock; - cpuset_cpus_allowed(p, &cpus_allowed); - cpus_and(new_mask, new_mask, cpus_allowed); + cpuset_cpus_allowed(p, cpus_allowed); + cpumask_and(new_mask, in_mask, cpus_allowed); again: - retval = set_cpus_allowed_ptr(p, &new_mask); + retval = set_cpus_allowed_ptr(p, new_mask); if (!retval) { - cpuset_cpus_allowed(p, &cpus_allowed); - if (!cpus_subset(new_mask, cpus_allowed)) { + cpuset_cpus_allowed(p, cpus_allowed); + if (!cpumask_subset(new_mask, cpus_allowed)) { /* * We must have raced with a concurrent cpuset * update. Just reset the cpus_allowed to the * cpuset's cpus_allowed */ - new_mask = cpus_allowed; + cpumask_copy(new_mask, cpus_allowed); goto again; } } out_unlock: + free_cpumask_var(new_mask); +out_free_cpus_allowed: + free_cpumask_var(cpus_allowed); +out_put_task: put_task_struct(p); put_online_cpus(); return retval; } static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, - cpumask_t *new_mask) + struct cpumask *new_mask) { - if (len < sizeof(cpumask_t)) { - memset(new_mask, 0, sizeof(cpumask_t)); - } else if (len > sizeof(cpumask_t)) { - len = sizeof(cpumask_t); - } + if (len < cpumask_size()) + cpumask_clear(new_mask); + else if (len > cpumask_size()) + len = cpumask_size(); + return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; } @@ -5477,17 +5600,20 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, unsigned long __user *user_mask_ptr) { - cpumask_t new_mask; + cpumask_var_t new_mask; int retval; - retval = get_user_cpu_mask(user_mask_ptr, len, &new_mask); - if (retval) - return retval; + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; - return sched_setaffinity(pid, &new_mask); + retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval == 0) + retval = sched_setaffinity(pid, new_mask); + free_cpumask_var(new_mask); + return retval; } -long sched_getaffinity(pid_t pid, cpumask_t *mask) +long sched_getaffinity(pid_t pid, struct cpumask *mask) { struct task_struct *p; int retval; @@ -5504,7 +5630,7 @@ long sched_getaffinity(pid_t pid, cpumask_t *mask) if (retval) goto out_unlock; - cpus_and(*mask, p->cpus_allowed, cpu_online_map); + cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); out_unlock: read_unlock(&tasklist_lock); @@ -5523,19 +5649,24 @@ asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len, unsigned long __user *user_mask_ptr) { int ret; - cpumask_t mask; + cpumask_var_t mask; - if (len < sizeof(cpumask_t)) + if (len < cpumask_size()) return -EINVAL; - ret = sched_getaffinity(pid, &mask); - if (ret < 0) - return ret; + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; - if (copy_to_user(user_mask_ptr, &mask, sizeof(cpumask_t))) - return -EFAULT; + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + if (copy_to_user(user_mask_ptr, mask, cpumask_size())) + ret = -EFAULT; + else + ret = cpumask_size(); + } + free_cpumask_var(mask); - return sizeof(cpumask_t); + return ret; } /** @@ -5877,7 +6008,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) idle->se.exec_start = sched_clock(); idle->prio = idle->normal_prio = MAX_PRIO; - idle->cpus_allowed = cpumask_of_cpu(cpu); + cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); __set_task_cpu(idle, cpu); rq->curr = rq->idle = idle; @@ -5896,6 +6027,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) * The idle tasks have their own, simple scheduling class: */ idle->sched_class = &idle_sched_class; + ftrace_graph_init_task(idle); } /* @@ -5903,9 +6035,9 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) * indicates which cpus entered this state. This is used * in the rcu update to wait only for active cpus. For system * which do not switch off the HZ timer nohz_cpu_mask should - * always be CPU_MASK_NONE. + * always be CPU_BITS_NONE. */ -cpumask_t nohz_cpu_mask = CPU_MASK_NONE; +cpumask_var_t nohz_cpu_mask; /* * Increase the granularity value when there are more CPUs, @@ -5960,7 +6092,7 @@ static inline void sched_init_granularity(void) * task must not exit() & deallocate itself prematurely. The * call is not atomic; no spinlocks may be held. */ -int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask) +int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { struct migration_req req; unsigned long flags; @@ -5968,13 +6100,13 @@ int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask) int ret = 0; rq = task_rq_lock(p, &flags); - if (!cpus_intersects(*new_mask, cpu_online_map)) { + if (!cpumask_intersects(new_mask, cpu_online_mask)) { ret = -EINVAL; goto out; } if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && - !cpus_equal(p->cpus_allowed, *new_mask))) { + !cpumask_equal(&p->cpus_allowed, new_mask))) { ret = -EINVAL; goto out; } @@ -5982,15 +6114,15 @@ int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask) if (p->sched_class->set_cpus_allowed) p->sched_class->set_cpus_allowed(p, new_mask); else { - p->cpus_allowed = *new_mask; - p->rt.nr_cpus_allowed = cpus_weight(*new_mask); + cpumask_copy(&p->cpus_allowed, new_mask); + p->rt.nr_cpus_allowed = cpumask_weight(new_mask); } /* Can the task run on the task's current CPU? If so, we're done */ - if (cpu_isset(task_cpu(p), *new_mask)) + if (cpumask_test_cpu(task_cpu(p), new_mask)) goto out; - if (migrate_task(p, any_online_cpu(*new_mask), &req)) { + if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) { /* Need help from migration thread: drop lock and wait. */ task_rq_unlock(rq, &flags); wake_up_process(rq->migration_thread); @@ -6032,7 +6164,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) if (task_cpu(p) != src_cpu) goto done; /* Affinity changed (again). */ - if (!cpu_isset(dest_cpu, p->cpus_allowed)) + if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) goto fail; on_rq = p->se.on_rq; @@ -6126,54 +6258,44 @@ static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu) /* * Figure out where task on dead CPU should go, use force if necessary. - * NOTE: interrupts should be disabled by the caller */ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) { - unsigned long flags; - cpumask_t mask; - struct rq *rq; int dest_cpu; + const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu)); - do { - /* On same node? */ - mask = node_to_cpumask(cpu_to_node(dead_cpu)); - cpus_and(mask, mask, p->cpus_allowed); - dest_cpu = any_online_cpu(mask); +again: + /* Look for allowed, online CPU in same node. */ + for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask) + if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + goto move; - /* On any allowed CPU? */ - if (dest_cpu >= nr_cpu_ids) - dest_cpu = any_online_cpu(p->cpus_allowed); + /* Any allowed, online CPU? */ + dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask); + if (dest_cpu < nr_cpu_ids) + goto move; - /* No more Mr. Nice Guy. */ - if (dest_cpu >= nr_cpu_ids) { - cpumask_t cpus_allowed; + /* No more Mr. Nice Guy. */ + if (dest_cpu >= nr_cpu_ids) { + cpuset_cpus_allowed_locked(p, &p->cpus_allowed); + dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed); - cpuset_cpus_allowed_locked(p, &cpus_allowed); - /* - * Try to stay on the same cpuset, where the - * current cpuset may be a subset of all cpus. - * The cpuset_cpus_allowed_locked() variant of - * cpuset_cpus_allowed() will not block. It must be - * called within calls to cpuset_lock/cpuset_unlock. - */ - rq = task_rq_lock(p, &flags); - p->cpus_allowed = cpus_allowed; - dest_cpu = any_online_cpu(p->cpus_allowed); - task_rq_unlock(rq, &flags); - - /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. - */ - if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no " - "longer affine to cpu%d\n", - task_pid_nr(p), p->comm, dead_cpu); - } + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk(KERN_INFO "process %d (%s) no " + "longer affine to cpu%d\n", + task_pid_nr(p), p->comm, dead_cpu); } - } while (!__migrate_task_irq(p, dead_cpu, dest_cpu)); + } + +move: + /* It can have affinity changed while we were choosing. */ + if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu))) + goto again; } /* @@ -6185,7 +6307,7 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) */ static void migrate_nr_uninterruptible(struct rq *rq_src) { - struct rq *rq_dest = cpu_rq(any_online_cpu(*CPU_MASK_ALL_PTR)); + struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask)); unsigned long flags; local_irq_save(flags); @@ -6475,7 +6597,7 @@ static void set_rq_online(struct rq *rq) if (!rq->online) { const struct sched_class *class; - cpu_set(rq->cpu, rq->rd->online); + cpumask_set_cpu(rq->cpu, rq->rd->online); rq->online = 1; for_each_class(class) { @@ -6495,7 +6617,7 @@ static void set_rq_offline(struct rq *rq) class->rq_offline(rq); } - cpu_clear(rq->cpu, rq->rd->online); + cpumask_clear_cpu(rq->cpu, rq->rd->online); rq->online = 0; } } @@ -6536,7 +6658,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) rq = cpu_rq(cpu); spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { - BUG_ON(!cpu_isset(cpu, rq->rd->span)); + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_online(rq); } @@ -6550,7 +6672,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) break; /* Unbind it from offline cpu so it can run. Fall thru. */ kthread_bind(cpu_rq(cpu)->migration_thread, - any_online_cpu(cpu_online_map)); + cpumask_any(cpu_online_mask)); kthread_stop(cpu_rq(cpu)->migration_thread); cpu_rq(cpu)->migration_thread = NULL; break; @@ -6600,7 +6722,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) rq = cpu_rq(cpu); spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { - BUG_ON(!cpu_isset(cpu, rq->rd->span)); + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_offline(rq); } spin_unlock_irqrestore(&rq->lock, flags); @@ -6638,36 +6760,14 @@ early_initcall(migration_init); #ifdef CONFIG_SCHED_DEBUG -static inline const char *sd_level_to_string(enum sched_domain_level lvl) -{ - switch (lvl) { - case SD_LV_NONE: - return "NONE"; - case SD_LV_SIBLING: - return "SIBLING"; - case SD_LV_MC: - return "MC"; - case SD_LV_CPU: - return "CPU"; - case SD_LV_NODE: - return "NODE"; - case SD_LV_ALLNODES: - return "ALLNODES"; - case SD_LV_MAX: - return "MAX"; - - } - return "MAX"; -} - static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, - cpumask_t *groupmask) + struct cpumask *groupmask) { struct sched_group *group = sd->groups; char str[256]; - cpulist_scnprintf(str, sizeof(str), sd->span); - cpus_clear(*groupmask); + cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd)); + cpumask_clear(groupmask); printk(KERN_DEBUG "%*s domain %d: ", level, "", level); @@ -6679,14 +6779,13 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, return -1; } - printk(KERN_CONT "span %s level %s\n", - str, sd_level_to_string(sd->level)); + printk(KERN_CONT "span %s level %s\n", str, sd->name); - if (!cpu_isset(cpu, sd->span)) { + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain " "CPU%d\n", cpu); } - if (!cpu_isset(cpu, group->cpumask)) { + if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { printk(KERN_ERR "ERROR: domain->groups does not contain" " CPU%d\n", cpu); } @@ -6706,31 +6805,32 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (!cpus_weight(group->cpumask)) { + if (!cpumask_weight(sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: empty group\n"); break; } - if (cpus_intersects(*groupmask, group->cpumask)) { + if (cpumask_intersects(groupmask, sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: repeated CPUs\n"); break; } - cpus_or(*groupmask, *groupmask, group->cpumask); + cpumask_or(groupmask, groupmask, sched_group_cpus(group)); - cpulist_scnprintf(str, sizeof(str), group->cpumask); + cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); printk(KERN_CONT " %s", str); group = group->next; } while (group != sd->groups); printk(KERN_CONT "\n"); - if (!cpus_equal(sd->span, *groupmask)) + if (!cpumask_equal(sched_domain_span(sd), groupmask)) printk(KERN_ERR "ERROR: groups don't span domain->span\n"); - if (sd->parent && !cpus_subset(*groupmask, sd->parent->span)) + if (sd->parent && + !cpumask_subset(groupmask, sched_domain_span(sd->parent))) printk(KERN_ERR "ERROR: parent span is not a superset " "of domain->span\n"); return 0; @@ -6738,7 +6838,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, static void sched_domain_debug(struct sched_domain *sd, int cpu) { - cpumask_t *groupmask; + cpumask_var_t groupmask; int level = 0; if (!sd) { @@ -6748,8 +6848,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); - groupmask = kmalloc(sizeof(cpumask_t), GFP_KERNEL); - if (!groupmask) { + if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) { printk(KERN_DEBUG "Cannot load-balance (out of memory)\n"); return; } @@ -6762,7 +6861,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) if (!sd) break; } - kfree(groupmask); + free_cpumask_var(groupmask); } #else /* !CONFIG_SCHED_DEBUG */ # define sched_domain_debug(sd, cpu) do { } while (0) @@ -6770,7 +6869,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) static int sd_degenerate(struct sched_domain *sd) { - if (cpus_weight(sd->span) == 1) + if (cpumask_weight(sched_domain_span(sd)) == 1) return 1; /* Following flags need at least 2 groups */ @@ -6801,7 +6900,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) if (sd_degenerate(parent)) return 1; - if (!cpus_equal(sd->span, parent->span)) + if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) return 0; /* Does parent contain flags not in child? */ @@ -6816,6 +6915,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_EXEC | SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES); + if (nr_node_ids == 1) + pflags &= ~SD_SERIALIZE; } if (~cflags & pflags) return 0; @@ -6823,6 +6924,16 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) return 1; } +static void free_rootdomain(struct root_domain *rd) +{ + cpupri_cleanup(&rd->cpupri); + + free_cpumask_var(rd->rto_mask); + free_cpumask_var(rd->online); + free_cpumask_var(rd->span); + kfree(rd); +} + static void rq_attach_root(struct rq *rq, struct root_domain *rd) { unsigned long flags; @@ -6832,38 +6943,62 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) if (rq->rd) { struct root_domain *old_rd = rq->rd; - if (cpu_isset(rq->cpu, old_rd->online)) + if (cpumask_test_cpu(rq->cpu, old_rd->online)) set_rq_offline(rq); - cpu_clear(rq->cpu, old_rd->span); + cpumask_clear_cpu(rq->cpu, old_rd->span); if (atomic_dec_and_test(&old_rd->refcount)) - kfree(old_rd); + free_rootdomain(old_rd); } atomic_inc(&rd->refcount); rq->rd = rd; - cpu_set(rq->cpu, rd->span); - if (cpu_isset(rq->cpu, cpu_online_map)) + cpumask_set_cpu(rq->cpu, rd->span); + if (cpumask_test_cpu(rq->cpu, cpu_online_mask)) set_rq_online(rq); spin_unlock_irqrestore(&rq->lock, flags); } -static void init_rootdomain(struct root_domain *rd) +static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem) { memset(rd, 0, sizeof(*rd)); - cpus_clear(rd->span); - cpus_clear(rd->online); + if (bootmem) { + alloc_bootmem_cpumask_var(&def_root_domain.span); + alloc_bootmem_cpumask_var(&def_root_domain.online); + alloc_bootmem_cpumask_var(&def_root_domain.rto_mask); + cpupri_init(&rd->cpupri, true); + return 0; + } + + if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + goto out; + if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + goto free_span; + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_online; - cpupri_init(&rd->cpupri); + if (cpupri_init(&rd->cpupri, false) != 0) + goto free_rto_mask; + return 0; + +free_rto_mask: + free_cpumask_var(rd->rto_mask); +free_online: + free_cpumask_var(rd->online); +free_span: + free_cpumask_var(rd->span); +out: + return -ENOMEM; } static void init_defrootdomain(void) { - init_rootdomain(&def_root_domain); + init_rootdomain(&def_root_domain, true); + atomic_set(&def_root_domain.refcount, 1); } @@ -6875,7 +7010,10 @@ static struct root_domain *alloc_rootdomain(void) if (!rd) return NULL; - init_rootdomain(rd); + if (init_rootdomain(rd, false) != 0) { + kfree(rd); + return NULL; + } return rd; } @@ -6917,19 +7055,12 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) } /* cpus with isolated domains */ -static cpumask_t cpu_isolated_map = CPU_MASK_NONE; +static cpumask_var_t cpu_isolated_map; /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { - static int __initdata ints[NR_CPUS]; - int i; - - str = get_options(str, ARRAY_SIZE(ints), ints); - cpus_clear(cpu_isolated_map); - for (i = 1; i <= ints[0]; i++) - if (ints[i] < NR_CPUS) - cpu_set(ints[i], cpu_isolated_map); + cpulist_parse(str, cpu_isolated_map); return 1; } @@ -6938,42 +7069,43 @@ __setup("isolcpus=", isolated_cpu_setup); /* * init_sched_build_groups takes the cpumask we wish to span, and a pointer * to a function which identifies what group(along with sched group) a CPU - * belongs to. The return value of group_fn must be a >= 0 and < NR_CPUS - * (due to the fact that we keep track of groups covered with a cpumask_t). + * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids + * (due to the fact that we keep track of groups covered with a struct cpumask). * * init_sched_build_groups will build a circular linked list of the groups * covered by the given span, and will set each group's ->cpumask correctly, * and ->cpu_power to 0. */ static void -init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map, - int (*group_fn)(int cpu, const cpumask_t *cpu_map, +init_sched_build_groups(const struct cpumask *span, + const struct cpumask *cpu_map, + int (*group_fn)(int cpu, const struct cpumask *cpu_map, struct sched_group **sg, - cpumask_t *tmpmask), - cpumask_t *covered, cpumask_t *tmpmask) + struct cpumask *tmpmask), + struct cpumask *covered, struct cpumask *tmpmask) { struct sched_group *first = NULL, *last = NULL; int i; - cpus_clear(*covered); + cpumask_clear(covered); - for_each_cpu_mask_nr(i, *span) { + for_each_cpu(i, span) { struct sched_group *sg; int group = group_fn(i, cpu_map, &sg, tmpmask); int j; - if (cpu_isset(i, *covered)) + if (cpumask_test_cpu(i, covered)) continue; - cpus_clear(sg->cpumask); + cpumask_clear(sched_group_cpus(sg)); sg->__cpu_power = 0; - for_each_cpu_mask_nr(j, *span) { + for_each_cpu(j, span) { if (group_fn(j, cpu_map, NULL, tmpmask) != group) continue; - cpu_set(j, *covered); - cpu_set(j, sg->cpumask); + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); } if (!first) first = sg; @@ -7037,23 +7169,21 @@ static int find_next_best_node(int node, nodemask_t *used_nodes) * should be one that prevents unnecessary balancing, but also spreads tasks * out optimally. */ -static void sched_domain_node_span(int node, cpumask_t *span) +static void sched_domain_node_span(int node, struct cpumask *span) { nodemask_t used_nodes; - node_to_cpumask_ptr(nodemask, node); int i; - cpus_clear(*span); + cpumask_clear(span); nodes_clear(used_nodes); - cpus_or(*span, *span, *nodemask); + cpumask_or(span, span, cpumask_of_node(node)); node_set(node, used_nodes); for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { int next_node = find_next_best_node(node, &used_nodes); - node_to_cpumask_ptr_next(nodemask, next_node); - cpus_or(*span, *span, *nodemask); + cpumask_or(span, span, cpumask_of_node(next_node)); } } #endif /* CONFIG_NUMA */ @@ -7061,18 +7191,33 @@ static void sched_domain_node_span(int node, cpumask_t *span) int sched_smt_power_savings = 0, sched_mc_power_savings = 0; /* + * The cpus mask in sched_group and sched_domain hangs off the end. + * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space + * for nr_cpu_ids < CONFIG_NR_CPUS. + */ +struct static_sched_group { + struct sched_group sg; + DECLARE_BITMAP(cpus, CONFIG_NR_CPUS); +}; + +struct static_sched_domain { + struct sched_domain sd; + DECLARE_BITMAP(span, CONFIG_NR_CPUS); +}; + +/* * SMT sched-domains: */ #ifdef CONFIG_SCHED_SMT -static DEFINE_PER_CPU(struct sched_domain, cpu_domains); -static DEFINE_PER_CPU(struct sched_group, sched_group_cpus); +static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus); static int -cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, - cpumask_t *unused) +cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *unused) { if (sg) - *sg = &per_cpu(sched_group_cpus, cpu); + *sg = &per_cpu(sched_group_cpus, cpu).sg; return cpu; } #endif /* CONFIG_SCHED_SMT */ @@ -7081,56 +7226,53 @@ cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, * multi-core sched-domains: */ #ifdef CONFIG_SCHED_MC -static DEFINE_PER_CPU(struct sched_domain, core_domains); -static DEFINE_PER_CPU(struct sched_group, sched_group_core); +static DEFINE_PER_CPU(struct static_sched_domain, core_domains); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); #endif /* CONFIG_SCHED_MC */ #if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT) static int -cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, - cpumask_t *mask) +cpu_to_core_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *mask) { int group; - *mask = per_cpu(cpu_sibling_map, cpu); - cpus_and(*mask, *mask, *cpu_map); - group = first_cpu(*mask); + cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map); + group = cpumask_first(mask); if (sg) - *sg = &per_cpu(sched_group_core, group); + *sg = &per_cpu(sched_group_core, group).sg; return group; } #elif defined(CONFIG_SCHED_MC) static int -cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, - cpumask_t *unused) +cpu_to_core_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *unused) { if (sg) - *sg = &per_cpu(sched_group_core, cpu); + *sg = &per_cpu(sched_group_core, cpu).sg; return cpu; } #endif -static DEFINE_PER_CPU(struct sched_domain, phys_domains); -static DEFINE_PER_CPU(struct sched_group, sched_group_phys); +static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); static int -cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, - cpumask_t *mask) +cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *mask) { int group; #ifdef CONFIG_SCHED_MC - *mask = cpu_coregroup_map(cpu); - cpus_and(*mask, *mask, *cpu_map); - group = first_cpu(*mask); + cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); + group = cpumask_first(mask); #elif defined(CONFIG_SCHED_SMT) - *mask = per_cpu(cpu_sibling_map, cpu); - cpus_and(*mask, *mask, *cpu_map); - group = first_cpu(*mask); + cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map); + group = cpumask_first(mask); #else group = cpu; #endif if (sg) - *sg = &per_cpu(sched_group_phys, group); + *sg = &per_cpu(sched_group_phys, group).sg; return group; } @@ -7144,19 +7286,19 @@ static DEFINE_PER_CPU(struct sched_domain, node_domains); static struct sched_group ***sched_group_nodes_bycpu; static DEFINE_PER_CPU(struct sched_domain, allnodes_domains); -static DEFINE_PER_CPU(struct sched_group, sched_group_allnodes); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes); -static int cpu_to_allnodes_group(int cpu, const cpumask_t *cpu_map, - struct sched_group **sg, cpumask_t *nodemask) +static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, + struct cpumask *nodemask) { int group; - *nodemask = node_to_cpumask(cpu_to_node(cpu)); - cpus_and(*nodemask, *nodemask, *cpu_map); - group = first_cpu(*nodemask); + cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map); + group = cpumask_first(nodemask); if (sg) - *sg = &per_cpu(sched_group_allnodes, group); + *sg = &per_cpu(sched_group_allnodes, group).sg; return group; } @@ -7168,11 +7310,11 @@ static void init_numa_sched_groups_power(struct sched_group *group_head) if (!sg) return; do { - for_each_cpu_mask_nr(j, sg->cpumask) { + for_each_cpu(j, sched_group_cpus(sg)) { struct sched_domain *sd; - sd = &per_cpu(phys_domains, j); - if (j != first_cpu(sd->groups->cpumask)) { + sd = &per_cpu(phys_domains, j).sd; + if (j != cpumask_first(sched_group_cpus(sd->groups))) { /* * Only add "power" once for each * physical package. @@ -7189,11 +7331,12 @@ static void init_numa_sched_groups_power(struct sched_group *group_head) #ifdef CONFIG_NUMA /* Free memory allocated for various sched_group structures */ -static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask) +static void free_sched_groups(const struct cpumask *cpu_map, + struct cpumask *nodemask) { int cpu, i; - for_each_cpu_mask_nr(cpu, *cpu_map) { + for_each_cpu(cpu, cpu_map) { struct sched_group **sched_group_nodes = sched_group_nodes_bycpu[cpu]; @@ -7203,9 +7346,8 @@ static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask) for (i = 0; i < nr_node_ids; i++) { struct sched_group *oldsg, *sg = sched_group_nodes[i]; - *nodemask = node_to_cpumask(i); - cpus_and(*nodemask, *nodemask, *cpu_map); - if (cpus_empty(*nodemask)) + cpumask_and(nodemask, cpumask_of_node(i), cpu_map); + if (cpumask_empty(nodemask)) continue; if (sg == NULL) @@ -7223,7 +7365,8 @@ next_sg: } } #else /* !CONFIG_NUMA */ -static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask) +static void free_sched_groups(const struct cpumask *cpu_map, + struct cpumask *nodemask) { } #endif /* CONFIG_NUMA */ @@ -7249,7 +7392,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) WARN_ON(!sd || !sd->groups); - if (cpu != first_cpu(sd->groups->cpumask)) + if (cpu != cpumask_first(sched_group_cpus(sd->groups))) return; child = sd->child; @@ -7314,40 +7457,6 @@ SD_INIT_FUNC(CPU) SD_INIT_FUNC(MC) #endif -/* - * To minimize stack usage kmalloc room for cpumasks and share the - * space as the usage in build_sched_domains() dictates. Used only - * if the amount of space is significant. - */ -struct allmasks { - cpumask_t tmpmask; /* make this one first */ - union { - cpumask_t nodemask; - cpumask_t this_sibling_map; - cpumask_t this_core_map; - }; - cpumask_t send_covered; - -#ifdef CONFIG_NUMA - cpumask_t domainspan; - cpumask_t covered; - cpumask_t notcovered; -#endif -}; - -#if NR_CPUS > 128 -#define SCHED_CPUMASK_ALLOC 1 -#define SCHED_CPUMASK_FREE(v) kfree(v) -#define SCHED_CPUMASK_DECLARE(v) struct allmasks *v -#else -#define SCHED_CPUMASK_ALLOC 0 -#define SCHED_CPUMASK_FREE(v) -#define SCHED_CPUMASK_DECLARE(v) struct allmasks _v, *v = &_v -#endif - -#define SCHED_CPUMASK_VAR(v, a) cpumask_t *v = (cpumask_t *) \ - ((unsigned long)(a) + offsetof(struct allmasks, v)) - static int default_relax_domain_level = -1; static int __init setup_relax_domain_level(char *str) @@ -7387,17 +7496,38 @@ static void set_domain_attribute(struct sched_domain *sd, * Build sched domains for a given set of cpus and attach the sched domains * to the individual cpus */ -static int __build_sched_domains(const cpumask_t *cpu_map, +static int __build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr) { - int i; + int i, err = -ENOMEM; struct root_domain *rd; - SCHED_CPUMASK_DECLARE(allmasks); - cpumask_t *tmpmask; + cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered, + tmpmask; #ifdef CONFIG_NUMA + cpumask_var_t domainspan, covered, notcovered; struct sched_group **sched_group_nodes = NULL; int sd_allnodes = 0; + if (!alloc_cpumask_var(&domainspan, GFP_KERNEL)) + goto out; + if (!alloc_cpumask_var(&covered, GFP_KERNEL)) + goto free_domainspan; + if (!alloc_cpumask_var(¬covered, GFP_KERNEL)) + goto free_covered; +#endif + + if (!alloc_cpumask_var(&nodemask, GFP_KERNEL)) + goto free_notcovered; + if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL)) + goto free_nodemask; + if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL)) + goto free_this_sibling_map; + if (!alloc_cpumask_var(&send_covered, GFP_KERNEL)) + goto free_this_core_map; + if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) + goto free_send_covered; + +#ifdef CONFIG_NUMA /* * Allocate the per-node list of sched groups */ @@ -7405,55 +7535,35 @@ static int __build_sched_domains(const cpumask_t *cpu_map, GFP_KERNEL); if (!sched_group_nodes) { printk(KERN_WARNING "Can not alloc sched group node list\n"); - return -ENOMEM; + goto free_tmpmask; } #endif rd = alloc_rootdomain(); if (!rd) { printk(KERN_WARNING "Cannot alloc root domain\n"); -#ifdef CONFIG_NUMA - kfree(sched_group_nodes); -#endif - return -ENOMEM; + goto free_sched_groups; } -#if SCHED_CPUMASK_ALLOC - /* get space for all scratch cpumask variables */ - allmasks = kmalloc(sizeof(*allmasks), GFP_KERNEL); - if (!allmasks) { - printk(KERN_WARNING "Cannot alloc cpumask array\n"); - kfree(rd); #ifdef CONFIG_NUMA - kfree(sched_group_nodes); -#endif - return -ENOMEM; - } -#endif - tmpmask = (cpumask_t *)allmasks; - - -#ifdef CONFIG_NUMA - sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes; + sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes; #endif /* * Set up domains for cpus specified by the cpu_map. */ - for_each_cpu_mask_nr(i, *cpu_map) { + for_each_cpu(i, cpu_map) { struct sched_domain *sd = NULL, *p; - SCHED_CPUMASK_VAR(nodemask, allmasks); - *nodemask = node_to_cpumask(cpu_to_node(i)); - cpus_and(*nodemask, *nodemask, *cpu_map); + cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map); #ifdef CONFIG_NUMA - if (cpus_weight(*cpu_map) > - SD_NODES_PER_DOMAIN*cpus_weight(*nodemask)) { + if (cpumask_weight(cpu_map) > + SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) { sd = &per_cpu(allnodes_domains, i); SD_INIT(sd, ALLNODES); set_domain_attribute(sd, attr); - sd->span = *cpu_map; + cpumask_copy(sched_domain_span(sd), cpu_map); cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask); p = sd; sd_allnodes = 1; @@ -7463,18 +7573,19 @@ static int __build_sched_domains(const cpumask_t *cpu_map, sd = &per_cpu(node_domains, i); SD_INIT(sd, NODE); set_domain_attribute(sd, attr); - sched_domain_node_span(cpu_to_node(i), &sd->span); + sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); sd->parent = p; if (p) p->child = sd; - cpus_and(sd->span, sd->span, *cpu_map); + cpumask_and(sched_domain_span(sd), + sched_domain_span(sd), cpu_map); #endif p = sd; - sd = &per_cpu(phys_domains, i); + sd = &per_cpu(phys_domains, i).sd; SD_INIT(sd, CPU); set_domain_attribute(sd, attr); - sd->span = *nodemask; + cpumask_copy(sched_domain_span(sd), nodemask); sd->parent = p; if (p) p->child = sd; @@ -7482,11 +7593,11 @@ static int __build_sched_domains(const cpumask_t *cpu_map, #ifdef CONFIG_SCHED_MC p = sd; - sd = &per_cpu(core_domains, i); + sd = &per_cpu(core_domains, i).sd; SD_INIT(sd, MC); set_domain_attribute(sd, attr); - sd->span = cpu_coregroup_map(i); - cpus_and(sd->span, sd->span, *cpu_map); + cpumask_and(sched_domain_span(sd), cpu_map, + cpu_coregroup_mask(i)); sd->parent = p; p->child = sd; cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask); @@ -7494,11 +7605,11 @@ static int __build_sched_domains(const cpumask_t *cpu_map, #ifdef CONFIG_SCHED_SMT p = sd; - sd = &per_cpu(cpu_domains, i); + sd = &per_cpu(cpu_domains, i).sd; SD_INIT(sd, SIBLING); set_domain_attribute(sd, attr); - sd->span = per_cpu(cpu_sibling_map, i); - cpus_and(sd->span, sd->span, *cpu_map); + cpumask_and(sched_domain_span(sd), + &per_cpu(cpu_sibling_map, i), cpu_map); sd->parent = p; p->child = sd; cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask); @@ -7507,13 +7618,10 @@ static int __build_sched_domains(const cpumask_t *cpu_map, #ifdef CONFIG_SCHED_SMT /* Set up CPU (sibling) groups */ - for_each_cpu_mask_nr(i, *cpu_map) { - SCHED_CPUMASK_VAR(this_sibling_map, allmasks); - SCHED_CPUMASK_VAR(send_covered, allmasks); - - *this_sibling_map = per_cpu(cpu_sibling_map, i); - cpus_and(*this_sibling_map, *this_sibling_map, *cpu_map); - if (i != first_cpu(*this_sibling_map)) + for_each_cpu(i, cpu_map) { + cpumask_and(this_sibling_map, + &per_cpu(cpu_sibling_map, i), cpu_map); + if (i != cpumask_first(this_sibling_map)) continue; init_sched_build_groups(this_sibling_map, cpu_map, @@ -7524,13 +7632,9 @@ static int __build_sched_domains(const cpumask_t *cpu_map, #ifdef CONFIG_SCHED_MC /* Set up multi-core groups */ - for_each_cpu_mask_nr(i, *cpu_map) { - SCHED_CPUMASK_VAR(this_core_map, allmasks); - SCHED_CPUMASK_VAR(send_covered, allmasks); - - *this_core_map = cpu_coregroup_map(i); - cpus_and(*this_core_map, *this_core_map, *cpu_map); - if (i != first_cpu(*this_core_map)) + for_each_cpu(i, cpu_map) { + cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map); + if (i != cpumask_first(this_core_map)) continue; init_sched_build_groups(this_core_map, cpu_map, @@ -7541,12 +7645,8 @@ static int __build_sched_domains(const cpumask_t *cpu_map, /* Set up physical groups */ for (i = 0; i < nr_node_ids; i++) { - SCHED_CPUMASK_VAR(nodemask, allmasks); - SCHED_CPUMASK_VAR(send_covered, allmasks); - - *nodemask = node_to_cpumask(i); - cpus_and(*nodemask, *nodemask, *cpu_map); - if (cpus_empty(*nodemask)) + cpumask_and(nodemask, cpumask_of_node(i), cpu_map); + if (cpumask_empty(nodemask)) continue; init_sched_build_groups(nodemask, cpu_map, @@ -7557,8 +7657,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map, #ifdef CONFIG_NUMA /* Set up node groups */ if (sd_allnodes) { - SCHED_CPUMASK_VAR(send_covered, allmasks); - init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group, send_covered, tmpmask); @@ -7567,58 +7665,53 @@ static int __build_sched_domains(const cpumask_t *cpu_map, for (i = 0; i < nr_node_ids; i++) { /* Set up node groups */ struct sched_group *sg, *prev; - SCHED_CPUMASK_VAR(nodemask, allmasks); - SCHED_CPUMASK_VAR(domainspan, allmasks); - SCHED_CPUMASK_VAR(covered, allmasks); int j; - *nodemask = node_to_cpumask(i); - cpus_clear(*covered); - - cpus_and(*nodemask, *nodemask, *cpu_map); - if (cpus_empty(*nodemask)) { + cpumask_clear(covered); + cpumask_and(nodemask, cpumask_of_node(i), cpu_map); + if (cpumask_empty(nodemask)) { sched_group_nodes[i] = NULL; continue; } sched_domain_node_span(i, domainspan); - cpus_and(*domainspan, *domainspan, *cpu_map); + cpumask_and(domainspan, domainspan, cpu_map); - sg = kmalloc_node(sizeof(struct sched_group), GFP_KERNEL, i); + sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, i); if (!sg) { printk(KERN_WARNING "Can not alloc domain group for " "node %d\n", i); goto error; } sched_group_nodes[i] = sg; - for_each_cpu_mask_nr(j, *nodemask) { + for_each_cpu(j, nodemask) { struct sched_domain *sd; sd = &per_cpu(node_domains, j); sd->groups = sg; } sg->__cpu_power = 0; - sg->cpumask = *nodemask; + cpumask_copy(sched_group_cpus(sg), nodemask); sg->next = sg; - cpus_or(*covered, *covered, *nodemask); + cpumask_or(covered, covered, nodemask); prev = sg; for (j = 0; j < nr_node_ids; j++) { - SCHED_CPUMASK_VAR(notcovered, allmasks); int n = (i + j) % nr_node_ids; - node_to_cpumask_ptr(pnodemask, n); - cpus_complement(*notcovered, *covered); - cpus_and(*tmpmask, *notcovered, *cpu_map); - cpus_and(*tmpmask, *tmpmask, *domainspan); - if (cpus_empty(*tmpmask)) + cpumask_complement(notcovered, covered); + cpumask_and(tmpmask, notcovered, cpu_map); + cpumask_and(tmpmask, tmpmask, domainspan); + if (cpumask_empty(tmpmask)) break; - cpus_and(*tmpmask, *tmpmask, *pnodemask); - if (cpus_empty(*tmpmask)) + cpumask_and(tmpmask, tmpmask, cpumask_of_node(n)); + if (cpumask_empty(tmpmask)) continue; - sg = kmalloc_node(sizeof(struct sched_group), + sg = kmalloc_node(sizeof(struct sched_group) + + cpumask_size(), GFP_KERNEL, i); if (!sg) { printk(KERN_WARNING @@ -7626,9 +7719,9 @@ static int __build_sched_domains(const cpumask_t *cpu_map, goto error; } sg->__cpu_power = 0; - sg->cpumask = *tmpmask; + cpumask_copy(sched_group_cpus(sg), tmpmask); sg->next = prev->next; - cpus_or(*covered, *covered, *tmpmask); + cpumask_or(covered, covered, tmpmask); prev->next = sg; prev = sg; } @@ -7637,22 +7730,22 @@ static int __build_sched_domains(const cpumask_t *cpu_map, /* Calculate CPU power for physical packages and nodes */ #ifdef CONFIG_SCHED_SMT - for_each_cpu_mask_nr(i, *cpu_map) { - struct sched_domain *sd = &per_cpu(cpu_domains, i); + for_each_cpu(i, cpu_map) { + struct sched_domain *sd = &per_cpu(cpu_domains, i).sd; init_sched_groups_power(i, sd); } #endif #ifdef CONFIG_SCHED_MC - for_each_cpu_mask_nr(i, *cpu_map) { - struct sched_domain *sd = &per_cpu(core_domains, i); + for_each_cpu(i, cpu_map) { + struct sched_domain *sd = &per_cpu(core_domains, i).sd; init_sched_groups_power(i, sd); } #endif - for_each_cpu_mask_nr(i, *cpu_map) { - struct sched_domain *sd = &per_cpu(phys_domains, i); + for_each_cpu(i, cpu_map) { + struct sched_domain *sd = &per_cpu(phys_domains, i).sd; init_sched_groups_power(i, sd); } @@ -7664,56 +7757,87 @@ static int __build_sched_domains(const cpumask_t *cpu_map, if (sd_allnodes) { struct sched_group *sg; - cpu_to_allnodes_group(first_cpu(*cpu_map), cpu_map, &sg, + cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg, tmpmask); init_numa_sched_groups_power(sg); } #endif /* Attach the domains */ - for_each_cpu_mask_nr(i, *cpu_map) { + for_each_cpu(i, cpu_map) { struct sched_domain *sd; #ifdef CONFIG_SCHED_SMT - sd = &per_cpu(cpu_domains, i); + sd = &per_cpu(cpu_domains, i).sd; #elif defined(CONFIG_SCHED_MC) - sd = &per_cpu(core_domains, i); + sd = &per_cpu(core_domains, i).sd; #else - sd = &per_cpu(phys_domains, i); + sd = &per_cpu(phys_domains, i).sd; #endif cpu_attach_domain(sd, rd, i); } - SCHED_CPUMASK_FREE((void *)allmasks); - return 0; + err = 0; + +free_tmpmask: + free_cpumask_var(tmpmask); +free_send_covered: + free_cpumask_var(send_covered); +free_this_core_map: + free_cpumask_var(this_core_map); +free_this_sibling_map: + free_cpumask_var(this_sibling_map); +free_nodemask: + free_cpumask_var(nodemask); +free_notcovered: +#ifdef CONFIG_NUMA + free_cpumask_var(notcovered); +free_covered: + free_cpumask_var(covered); +free_domainspan: + free_cpumask_var(domainspan); +out: +#endif + return err; + +free_sched_groups: +#ifdef CONFIG_NUMA + kfree(sched_group_nodes); +#endif + goto free_tmpmask; #ifdef CONFIG_NUMA error: free_sched_groups(cpu_map, tmpmask); - SCHED_CPUMASK_FREE((void *)allmasks); - kfree(rd); - return -ENOMEM; + free_rootdomain(rd); + goto free_tmpmask; #endif } -static int build_sched_domains(const cpumask_t *cpu_map) +static int build_sched_domains(const struct cpumask *cpu_map) { return __build_sched_domains(cpu_map, NULL); } -static cpumask_t *doms_cur; /* current sched domains */ +static struct cpumask *doms_cur; /* current sched domains */ static int ndoms_cur; /* number of sched domains in 'doms_cur' */ static struct sched_domain_attr *dattr_cur; /* attribues of custom domains in 'doms_cur' */ /* * Special case: If a kmalloc of a doms_cur partition (array of - * cpumask_t) fails, then fallback to a single sched domain, - * as determined by the single cpumask_t fallback_doms. + * cpumask) fails, then fallback to a single sched domain, + * as determined by the single cpumask fallback_doms. */ -static cpumask_t fallback_doms; +static cpumask_var_t fallback_doms; -void __attribute__((weak)) arch_update_cpu_topology(void) +/* + * arch_update_cpu_topology lets virtualized architectures update the + * cpu core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __attribute__((weak)) arch_update_cpu_topology(void) { + return 0; } /* @@ -7721,16 +7845,16 @@ void __attribute__((weak)) arch_update_cpu_topology(void) * For now this just excludes isolated cpus, but could be used to * exclude other special cases in the future. */ -static int arch_init_sched_domains(const cpumask_t *cpu_map) +static int arch_init_sched_domains(const struct cpumask *cpu_map) { int err; arch_update_cpu_topology(); ndoms_cur = 1; - doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL); + doms_cur = kmalloc(cpumask_size(), GFP_KERNEL); if (!doms_cur) - doms_cur = &fallback_doms; - cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map); + doms_cur = fallback_doms; + cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map); dattr_cur = NULL; err = build_sched_domains(doms_cur); register_sched_domain_sysctl(); @@ -7738,8 +7862,8 @@ static int arch_init_sched_domains(const cpumask_t *cpu_map) return err; } -static void arch_destroy_sched_domains(const cpumask_t *cpu_map, - cpumask_t *tmpmask) +static void arch_destroy_sched_domains(const struct cpumask *cpu_map, + struct cpumask *tmpmask) { free_sched_groups(cpu_map, tmpmask); } @@ -7748,17 +7872,16 @@ static void arch_destroy_sched_domains(const cpumask_t *cpu_map, * Detach sched domains from a group of cpus specified in cpu_map * These cpus will now be attached to the NULL domain */ -static void detach_destroy_domains(const cpumask_t *cpu_map) +static void detach_destroy_domains(const struct cpumask *cpu_map) { - cpumask_t tmpmask; + /* Save because hotplug lock held. */ + static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS); int i; - unregister_sched_domain_sysctl(); - - for_each_cpu_mask_nr(i, *cpu_map) + for_each_cpu(i, cpu_map) cpu_attach_domain(NULL, &def_root_domain, i); synchronize_sched(); - arch_destroy_sched_domains(cpu_map, &tmpmask); + arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask)); } /* handle null as "default" */ @@ -7783,7 +7906,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * doms_new[] to the current sched domain partitioning, doms_cur[]. * It destroys each deleted domain and builds each new domain. * - * 'doms_new' is an array of cpumask_t's of length 'ndoms_new'. + * 'doms_new' is an array of cpumask's of length 'ndoms_new'. * The masks don't intersect (don't overlap.) We should setup one * sched domain for each mask. CPUs not in any of the cpumasks will * not be load balanced. If the same cpumask appears both in the @@ -7797,28 +7920,33 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * the single partition 'fallback_doms', it also forces the domains * to be rebuilt. * - * If doms_new == NULL it will be replaced with cpu_online_map. + * If doms_new == NULL it will be replaced with cpu_online_mask. * ndoms_new == 0 is a special case for destroying existing domains, * and it will not create the default domain. * * Call with hotplug lock held */ -void partition_sched_domains(int ndoms_new, cpumask_t *doms_new, +/* FIXME: Change to struct cpumask *doms_new[] */ +void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, struct sched_domain_attr *dattr_new) { int i, j, n; + int new_topology; mutex_lock(&sched_domains_mutex); /* always unregister in case we don't destroy any domains */ unregister_sched_domain_sysctl(); + /* Let architecture update cpu core mappings. */ + new_topology = arch_update_cpu_topology(); + n = doms_new ? ndoms_new : 0; /* Destroy deleted domains */ for (i = 0; i < ndoms_cur; i++) { - for (j = 0; j < n; j++) { - if (cpus_equal(doms_cur[i], doms_new[j]) + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(&doms_cur[i], &doms_new[j]) && dattrs_equal(dattr_cur, i, dattr_new, j)) goto match1; } @@ -7830,15 +7958,15 @@ match1: if (doms_new == NULL) { ndoms_cur = 0; - doms_new = &fallback_doms; - cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map); - dattr_new = NULL; + doms_new = fallback_doms; + cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map); + WARN_ON_ONCE(dattr_new); } /* Build new domains */ for (i = 0; i < ndoms_new; i++) { - for (j = 0; j < ndoms_cur; j++) { - if (cpus_equal(doms_new[i], doms_cur[j]) + for (j = 0; j < ndoms_cur && !new_topology; j++) { + if (cpumask_equal(&doms_new[i], &doms_cur[j]) && dattrs_equal(dattr_new, i, dattr_cur, j)) goto match2; } @@ -7850,7 +7978,7 @@ match2: } /* Remember the new sched domains */ - if (doms_cur != &fallback_doms) + if (doms_cur != fallback_doms) kfree(doms_cur); kfree(dattr_cur); /* kfree(NULL) is safe */ doms_cur = doms_new; @@ -7863,7 +7991,7 @@ match2: } #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -int arch_reinit_sched_domains(void) +static void arch_reinit_sched_domains(void) { get_online_cpus(); @@ -7872,25 +8000,33 @@ int arch_reinit_sched_domains(void) rebuild_sched_domains(); put_online_cpus(); - - return 0; } static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) { - int ret; + unsigned int level = 0; - if (buf[0] != '0' && buf[0] != '1') + if (sscanf(buf, "%u", &level) != 1) + return -EINVAL; + + /* + * level is always be positive so don't check for + * level < POWERSAVINGS_BALANCE_NONE which is 0 + * What happens on 0 or 1 byte write, + * need to check for count as well? + */ + + if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) return -EINVAL; if (smt) - sched_smt_power_savings = (buf[0] == '1'); + sched_smt_power_savings = level; else - sched_mc_power_savings = (buf[0] == '1'); + sched_mc_power_savings = level; - ret = arch_reinit_sched_domains(); + arch_reinit_sched_domains(); - return ret ? ret : count; + return count; } #ifdef CONFIG_SCHED_MC @@ -7925,7 +8061,7 @@ static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, sched_smt_power_savings_store); #endif -int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) +int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) { int err = 0; @@ -7990,7 +8126,9 @@ static int update_runtime(struct notifier_block *nfb, void __init sched_init_smp(void) { - cpumask_t non_isolated_cpus; + cpumask_var_t non_isolated_cpus; + + alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); #if defined(CONFIG_NUMA) sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), @@ -7999,10 +8137,10 @@ void __init sched_init_smp(void) #endif get_online_cpus(); mutex_lock(&sched_domains_mutex); - arch_init_sched_domains(&cpu_online_map); - cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map); - if (cpus_empty(non_isolated_cpus)) - cpu_set(smp_processor_id(), non_isolated_cpus); + arch_init_sched_domains(cpu_online_mask); + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + if (cpumask_empty(non_isolated_cpus)) + cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); mutex_unlock(&sched_domains_mutex); put_online_cpus(); @@ -8017,9 +8155,13 @@ void __init sched_init_smp(void) init_hrtick(); /* Move init over to a non-isolated CPU */ - if (set_cpus_allowed_ptr(current, &non_isolated_cpus) < 0) + if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) BUG(); sched_init_granularity(); + free_cpumask_var(non_isolated_cpus); + + alloc_cpumask_var(&fallback_doms, GFP_KERNEL); + init_sched_rt_class(); } #else void __init sched_init_smp(void) @@ -8334,6 +8476,15 @@ void __init sched_init(void) */ current->sched_class = &fair_sched_class; + /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ + alloc_bootmem_cpumask_var(&nohz_cpu_mask); +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ + alloc_bootmem_cpumask_var(&nohz.cpu_mask); +#endif + alloc_bootmem_cpumask_var(&cpu_isolated_map); +#endif /* SMP */ + scheduler_running = 1; } @@ -8492,7 +8643,7 @@ static int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) { struct cfs_rq *cfs_rq; - struct sched_entity *se, *parent_se; + struct sched_entity *se; struct rq *rq; int i; @@ -8508,18 +8659,17 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) for_each_possible_cpu(i) { rq = cpu_rq(i); - cfs_rq = kmalloc_node(sizeof(struct cfs_rq), - GFP_KERNEL|__GFP_ZERO, cpu_to_node(i)); + cfs_rq = kzalloc_node(sizeof(struct cfs_rq), + GFP_KERNEL, cpu_to_node(i)); if (!cfs_rq) goto err; - se = kmalloc_node(sizeof(struct sched_entity), - GFP_KERNEL|__GFP_ZERO, cpu_to_node(i)); + se = kzalloc_node(sizeof(struct sched_entity), + GFP_KERNEL, cpu_to_node(i)); if (!se) goto err; - parent_se = parent ? parent->se[i] : NULL; - init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent_se); + init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]); } return 1; @@ -8580,7 +8730,7 @@ static int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) { struct rt_rq *rt_rq; - struct sched_rt_entity *rt_se, *parent_se; + struct sched_rt_entity *rt_se; struct rq *rq; int i; @@ -8597,18 +8747,17 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) for_each_possible_cpu(i) { rq = cpu_rq(i); - rt_rq = kmalloc_node(sizeof(struct rt_rq), - GFP_KERNEL|__GFP_ZERO, cpu_to_node(i)); + rt_rq = kzalloc_node(sizeof(struct rt_rq), + GFP_KERNEL, cpu_to_node(i)); if (!rt_rq) goto err; - rt_se = kmalloc_node(sizeof(struct sched_rt_entity), - GFP_KERNEL|__GFP_ZERO, cpu_to_node(i)); + rt_se = kzalloc_node(sizeof(struct sched_rt_entity), + GFP_KERNEL, cpu_to_node(i)); if (!rt_se) goto err; - parent_se = parent ? parent->rt_se[i] : NULL; - init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent_se); + init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]); } return 1; @@ -9251,11 +9400,12 @@ struct cgroup_subsys cpu_cgroup_subsys = { * (balbir@in.ibm.com). */ -/* track cpu usage of a group of tasks */ +/* track cpu usage of a group of tasks and its child groups */ struct cpuacct { struct cgroup_subsys_state css; /* cpuusage holds pointer to a u64-type object on every cpu */ u64 *cpuusage; + struct cpuacct *parent; }; struct cgroup_subsys cpuacct_subsys; @@ -9289,6 +9439,9 @@ static struct cgroup_subsys_state *cpuacct_create( return ERR_PTR(-ENOMEM); } + if (cgrp->parent) + ca->parent = cgroup_ca(cgrp->parent); + return &ca->css; } @@ -9302,6 +9455,41 @@ cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) kfree(ca); } +static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) +{ + u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 data; + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit read safe on 32-bit platforms. + */ + spin_lock_irq(&cpu_rq(cpu)->lock); + data = *cpuusage; + spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + data = *cpuusage; +#endif + + return data; +} + +static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) +{ + u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit write safe on 32-bit platforms. + */ + spin_lock_irq(&cpu_rq(cpu)->lock); + *cpuusage = val; + spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + *cpuusage = val; +#endif +} + /* return total cpu usage (in nanoseconds) of a group */ static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) { @@ -9309,17 +9497,8 @@ static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) u64 totalcpuusage = 0; int i; - for_each_possible_cpu(i) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, i); - - /* - * Take rq->lock to make 64-bit addition safe on 32-bit - * platforms. - */ - spin_lock_irq(&cpu_rq(i)->lock); - totalcpuusage += *cpuusage; - spin_unlock_irq(&cpu_rq(i)->lock); - } + for_each_present_cpu(i) + totalcpuusage += cpuacct_cpuusage_read(ca, i); return totalcpuusage; } @@ -9336,23 +9515,39 @@ static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, goto out; } - for_each_possible_cpu(i) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, i); + for_each_present_cpu(i) + cpuacct_cpuusage_write(ca, i, 0); - spin_lock_irq(&cpu_rq(i)->lock); - *cpuusage = 0; - spin_unlock_irq(&cpu_rq(i)->lock); - } out: return err; } +static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, + struct seq_file *m) +{ + struct cpuacct *ca = cgroup_ca(cgroup); + u64 percpu; + int i; + + for_each_present_cpu(i) { + percpu = cpuacct_cpuusage_read(ca, i); + seq_printf(m, "%llu ", (unsigned long long) percpu); + } + seq_printf(m, "\n"); + return 0; +} + static struct cftype files[] = { { .name = "usage", .read_u64 = cpuusage_read, .write_u64 = cpuusage_write, }, + { + .name = "usage_percpu", + .read_seq_string = cpuacct_percpu_seq_read, + }, + }; static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) @@ -9368,14 +9563,16 @@ static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) static void cpuacct_charge(struct task_struct *tsk, u64 cputime) { struct cpuacct *ca; + int cpu; if (!cpuacct_subsys.active) return; + cpu = task_cpu(tsk); ca = task_ca(tsk); - if (ca) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk)); + for (; ca; ca = ca->parent) { + u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); *cpuusage += cputime; } } diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index e8ab096..a0b0852 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -124,7 +124,7 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now) clock = scd->tick_gtod + delta; min_clock = wrap_max(scd->tick_gtod, scd->clock); - max_clock = scd->tick_gtod + TICK_NSEC; + max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC); clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); @@ -227,6 +227,9 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event); */ void sched_clock_idle_wakeup_event(u64 delta_ns) { + if (timekeeping_suspended) + return; + sched_clock_tick(); touch_softlockup_watchdog(); } diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index 52154fe..1e00bfa 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -67,24 +67,21 @@ static int convert_prio(int prio) * Returns: (int)bool - CPUs were found */ int cpupri_find(struct cpupri *cp, struct task_struct *p, - cpumask_t *lowest_mask) + struct cpumask *lowest_mask) { int idx = 0; int task_pri = convert_prio(p->prio); for_each_cpupri_active(cp->pri_active, idx) { struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; - cpumask_t mask; if (idx >= task_pri) break; - cpus_and(mask, p->cpus_allowed, vec->mask); - - if (cpus_empty(mask)) + if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) continue; - *lowest_mask = mask; + cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); return 1; } @@ -126,7 +123,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) vec->count--; if (!vec->count) clear_bit(oldpri, cp->pri_active); - cpu_clear(cpu, vec->mask); + cpumask_clear_cpu(cpu, vec->mask); spin_unlock_irqrestore(&vec->lock, flags); } @@ -136,7 +133,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) spin_lock_irqsave(&vec->lock, flags); - cpu_set(cpu, vec->mask); + cpumask_set_cpu(cpu, vec->mask); vec->count++; if (vec->count == 1) set_bit(newpri, cp->pri_active); @@ -150,10 +147,11 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) /** * cpupri_init - initialize the cpupri structure * @cp: The cpupri context + * @bootmem: true if allocations need to use bootmem * - * Returns: (void) + * Returns: -ENOMEM if memory fails. */ -void cpupri_init(struct cpupri *cp) +int __init_refok cpupri_init(struct cpupri *cp, bool bootmem) { int i; @@ -164,11 +162,30 @@ void cpupri_init(struct cpupri *cp) spin_lock_init(&vec->lock); vec->count = 0; - cpus_clear(vec->mask); + if (bootmem) + alloc_bootmem_cpumask_var(&vec->mask); + else if (!alloc_cpumask_var(&vec->mask, GFP_KERNEL)) + goto cleanup; } for_each_possible_cpu(i) cp->cpu_to_pri[i] = CPUPRI_INVALID; + return 0; + +cleanup: + for (i--; i >= 0; i--) + free_cpumask_var(cp->pri_to_cpu[i].mask); + return -ENOMEM; } +/** + * cpupri_cleanup - clean up the cpupri structure + * @cp: The cpupri context + */ +void cpupri_cleanup(struct cpupri *cp) +{ + int i; + for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) + free_cpumask_var(cp->pri_to_cpu[i].mask); +} diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h index f25811b0..642a94e 100644 --- a/kernel/sched_cpupri.h +++ b/kernel/sched_cpupri.h @@ -14,7 +14,7 @@ struct cpupri_vec { spinlock_t lock; int count; - cpumask_t mask; + cpumask_var_t mask; }; struct cpupri { @@ -27,7 +27,8 @@ struct cpupri { int cpupri_find(struct cpupri *cp, struct task_struct *p, cpumask_t *lowest_mask); void cpupri_set(struct cpupri *cp, int cpu, int pri); -void cpupri_init(struct cpupri *cp); +int cpupri_init(struct cpupri *cp, bool bootmem); +void cpupri_cleanup(struct cpupri *cp); #else #define cpupri_set(cp, cpu, pri) do { } while (0) #define cpupri_init() do { } while (0) diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 26ed8e3..4293cfa 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -53,6 +53,40 @@ static unsigned long nsec_low(unsigned long long nsec) #define SPLIT_NS(x) nsec_high(x), nsec_low(x) +#ifdef CONFIG_FAIR_GROUP_SCHED +static void print_cfs_group_stats(struct seq_file *m, int cpu, + struct task_group *tg) +{ + struct sched_entity *se = tg->se[cpu]; + if (!se) + return; + +#define P(F) \ + SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F) +#define PN(F) \ + SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F)) + + PN(se->exec_start); + PN(se->vruntime); + PN(se->sum_exec_runtime); +#ifdef CONFIG_SCHEDSTATS + PN(se->wait_start); + PN(se->sleep_start); + PN(se->block_start); + PN(se->sleep_max); + PN(se->block_max); + PN(se->exec_max); + PN(se->slice_max); + PN(se->wait_max); + PN(se->wait_sum); + P(se->wait_count); +#endif + P(se->load.weight); +#undef PN +#undef P +} +#endif + static void print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) { @@ -121,20 +155,19 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) char path[128] = ""; - struct cgroup *cgroup = NULL; struct task_group *tg = cfs_rq->tg; - if (tg) - cgroup = tg->css.cgroup; - - if (cgroup) - cgroup_path(cgroup, path, sizeof(path)); + cgroup_path(tg->css.cgroup, path, sizeof(path)); SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path); +#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) + { + uid_t uid = cfs_rq->tg->uid; + SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid); + } #else SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); #endif - SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", SPLIT_NS(cfs_rq->exec_clock)); @@ -168,6 +201,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #ifdef CONFIG_SMP SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares); #endif + print_cfs_group_stats(m, cpu, cfs_rq->tg); #endif } @@ -175,14 +209,9 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) { #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED) char path[128] = ""; - struct cgroup *cgroup = NULL; struct task_group *tg = rt_rq->tg; - if (tg) - cgroup = tg->css.cgroup; - - if (cgroup) - cgroup_path(cgroup, path, sizeof(path)); + cgroup_path(tg->css.cgroup, path, sizeof(path)); SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path); #else @@ -272,7 +301,7 @@ static int sched_debug_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Sched Debug Version: v0.07, %s %.*s\n", + SEQ_printf(m, "Sched Debug Version: v0.08, %s %.*s\n", init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 98345e4..8e1352c 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -386,20 +386,6 @@ int sched_nr_latency_handler(struct ctl_table *table, int write, #endif /* - * delta *= P[w / rw] - */ -static inline unsigned long -calc_delta_weight(unsigned long delta, struct sched_entity *se) -{ - for_each_sched_entity(se) { - delta = calc_delta_mine(delta, - se->load.weight, &cfs_rq_of(se)->load); - } - - return delta; -} - -/* * delta /= w */ static inline unsigned long @@ -440,12 +426,20 @@ static u64 __sched_period(unsigned long nr_running) */ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - unsigned long nr_running = cfs_rq->nr_running; + u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq); - if (unlikely(!se->on_rq)) - nr_running++; + for_each_sched_entity(se) { + struct load_weight *load = &cfs_rq->load; - return calc_delta_weight(__sched_period(nr_running), se); + if (unlikely(!se->on_rq)) { + struct load_weight lw = cfs_rq->load; + + update_load_add(&lw, se->load.weight); + load = &lw; + } + slice = calc_delta_mine(slice, se->load.weight, load); + } + return slice; } /* @@ -492,6 +486,8 @@ static void update_curr(struct cfs_rq *cfs_rq) * overflow on 32 bits): */ delta_exec = (unsigned long)(now - curr->exec_start); + if (!delta_exec) + return; __update_curr(cfs_rq, curr, delta_exec); curr->exec_start = now; @@ -1017,16 +1013,33 @@ static void yield_task_fair(struct rq *rq) * search starts with cpus closest then further out as needed, * so we always favor a closer, idle cpu. * Domains may include CPUs that are not usable for migration, - * hence we need to mask them out (cpu_active_map) + * hence we need to mask them out (cpu_active_mask) * * Returns the CPU we should wake onto. */ #if defined(ARCH_HAS_SCHED_WAKE_IDLE) static int wake_idle(int cpu, struct task_struct *p) { - cpumask_t tmp; struct sched_domain *sd; int i; + unsigned int chosen_wakeup_cpu; + int this_cpu; + + /* + * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu + * are idle and this is not a kernel thread and this task's affinity + * allows it to be moved to preferred cpu, then just move! + */ + + this_cpu = smp_processor_id(); + chosen_wakeup_cpu = + cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu; + + if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP && + idle_cpu(cpu) && idle_cpu(this_cpu) && + p->mm && !(p->flags & PF_KTHREAD) && + cpu_isset(chosen_wakeup_cpu, p->cpus_allowed)) + return chosen_wakeup_cpu; /* * If it is idle, then it is the best cpu to run this task. @@ -1044,10 +1057,9 @@ static int wake_idle(int cpu, struct task_struct *p) if ((sd->flags & SD_WAKE_IDLE) || ((sd->flags & SD_WAKE_IDLE_FAR) && !task_hot(p, task_rq(p)->clock, sd))) { - cpus_and(tmp, sd->span, p->cpus_allowed); - cpus_and(tmp, tmp, cpu_active_map); - for_each_cpu_mask_nr(i, tmp) { - if (idle_cpu(i)) { + for_each_cpu_and(i, sched_domain_span(sd), + &p->cpus_allowed) { + if (cpu_active(i) && idle_cpu(i)) { if (i != task_cpu(p)) { schedstat_inc(p, se.nr_wakeups_idle); @@ -1240,13 +1252,13 @@ static int select_task_rq_fair(struct task_struct *p, int sync) * this_cpu and prev_cpu are present in: */ for_each_domain(this_cpu, sd) { - if (cpu_isset(prev_cpu, sd->span)) { + if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) { this_sd = sd; break; } } - if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed))) + if (unlikely(!cpumask_test_cpu(this_cpu, &p->cpus_allowed))) goto out; /* @@ -1345,12 +1357,11 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) { struct task_struct *curr = rq->curr; struct sched_entity *se = &curr->se, *pse = &p->se; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); - if (unlikely(rt_prio(p->prio))) { - struct cfs_rq *cfs_rq = task_cfs_rq(curr); + update_curr(cfs_rq); - update_rq_clock(rq); - update_curr(cfs_rq); + if (unlikely(rt_prio(p->prio))) { resched_task(curr); return; } @@ -1606,8 +1617,6 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) } } -#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0) - /* * Share the fairness runtime between parent and child, thus the * total amount of pressure for CPU stays equal - new tasks diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index d9ba9d5..954e1a8 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -15,7 +15,7 @@ static inline void rt_set_overload(struct rq *rq) if (!rq->online) return; - cpu_set(rq->cpu, rq->rd->rto_mask); + cpumask_set_cpu(rq->cpu, rq->rd->rto_mask); /* * Make sure the mask is visible before we set * the overload count. That is checked to determine @@ -34,7 +34,7 @@ static inline void rt_clear_overload(struct rq *rq) /* the order here really doesn't matter */ atomic_dec(&rq->rd->rto_count); - cpu_clear(rq->cpu, rq->rd->rto_mask); + cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask); } static void update_rt_migration(struct rq *rq) @@ -77,7 +77,7 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq) } #define for_each_leaf_rt_rq(rt_rq, rq) \ - list_for_each_entry(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list) + list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list) static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) { @@ -139,14 +139,14 @@ static int rt_se_boosted(struct sched_rt_entity *rt_se) } #ifdef CONFIG_SMP -static inline cpumask_t sched_rt_period_mask(void) +static inline const struct cpumask *sched_rt_period_mask(void) { return cpu_rq(smp_processor_id())->rd->span; } #else -static inline cpumask_t sched_rt_period_mask(void) +static inline const struct cpumask *sched_rt_period_mask(void) { - return cpu_online_map; + return cpu_online_mask; } #endif @@ -212,9 +212,9 @@ static inline int rt_rq_throttled(struct rt_rq *rt_rq) return rt_rq->rt_throttled; } -static inline cpumask_t sched_rt_period_mask(void) +static inline const struct cpumask *sched_rt_period_mask(void) { - return cpu_online_map; + return cpu_online_mask; } static inline @@ -241,11 +241,11 @@ static int do_balance_runtime(struct rt_rq *rt_rq) int i, weight, more = 0; u64 rt_period; - weight = cpus_weight(rd->span); + weight = cpumask_weight(rd->span); spin_lock(&rt_b->rt_runtime_lock); rt_period = ktime_to_ns(rt_b->rt_period); - for_each_cpu_mask_nr(i, rd->span) { + for_each_cpu(i, rd->span) { struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); s64 diff; @@ -324,7 +324,7 @@ static void __disable_runtime(struct rq *rq) /* * Greedy reclaim, take back as much as we can. */ - for_each_cpu_mask(i, rd->span) { + for_each_cpu(i, rd->span) { struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); s64 diff; @@ -429,13 +429,13 @@ static inline int balance_runtime(struct rt_rq *rt_rq) static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) { int i, idle = 1; - cpumask_t span; + const struct cpumask *span; if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) return 1; span = sched_rt_period_mask(); - for_each_cpu_mask(i, span) { + for_each_cpu(i, span) { int enqueue = 0; struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); struct rq *rq = rq_of_rt_rq(rt_rq); @@ -537,13 +537,13 @@ static void update_curr_rt(struct rq *rq) for_each_sched_rt_entity(rt_se) { rt_rq = rt_rq_of_se(rt_se); - spin_lock(&rt_rq->rt_runtime_lock); if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { + spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_time += delta_exec; if (sched_rt_runtime_exceeded(rt_rq)) resched_task(curr); + spin_unlock(&rt_rq->rt_runtime_lock); } - spin_unlock(&rt_rq->rt_runtime_lock); } } @@ -805,17 +805,20 @@ static int select_task_rq_rt(struct task_struct *p, int sync) static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) { - cpumask_t mask; + cpumask_var_t mask; if (rq->curr->rt.nr_cpus_allowed == 1) return; - if (p->rt.nr_cpus_allowed != 1 - && cpupri_find(&rq->rd->cpupri, p, &mask)) + if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) return; - if (!cpupri_find(&rq->rd->cpupri, rq->curr, &mask)) - return; + if (p->rt.nr_cpus_allowed != 1 + && cpupri_find(&rq->rd->cpupri, p, mask)) + goto free; + + if (!cpupri_find(&rq->rd->cpupri, rq->curr, mask)) + goto free; /* * There appears to be other cpus that can accept @@ -824,6 +827,8 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) */ requeue_task_rt(rq, p, 1); resched_task(rq->curr); +free: + free_cpumask_var(mask); } #endif /* CONFIG_SMP */ @@ -909,15 +914,12 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) /* Only try algorithms three times */ #define RT_MAX_TRIES 3 -static int double_lock_balance(struct rq *this_rq, struct rq *busiest); -static void double_unlock_balance(struct rq *this_rq, struct rq *busiest); - static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep); static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - (cpu < 0 || cpu_isset(cpu, p->cpus_allowed)) && + (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) && (p->rt.nr_cpus_allowed > 1)) return 1; return 0; @@ -956,7 +958,7 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu) return next; } -static DEFINE_PER_CPU(cpumask_t, local_cpu_mask); +static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask); static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask) { @@ -976,7 +978,7 @@ static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask) static int find_lowest_rq(struct task_struct *task) { struct sched_domain *sd; - cpumask_t *lowest_mask = &__get_cpu_var(local_cpu_mask); + struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask); int this_cpu = smp_processor_id(); int cpu = task_cpu(task); @@ -991,7 +993,7 @@ static int find_lowest_rq(struct task_struct *task) * I guess we might want to change cpupri_find() to ignore those * in the first place. */ - cpus_and(*lowest_mask, *lowest_mask, cpu_active_map); + cpumask_and(lowest_mask, lowest_mask, cpu_active_mask); /* * At this point we have built a mask of cpus representing the @@ -1001,7 +1003,7 @@ static int find_lowest_rq(struct task_struct *task) * We prioritize the last cpu that the task executed on since * it is most likely cache-hot in that location. */ - if (cpu_isset(cpu, *lowest_mask)) + if (cpumask_test_cpu(cpu, lowest_mask)) return cpu; /* @@ -1016,7 +1018,8 @@ static int find_lowest_rq(struct task_struct *task) cpumask_t domain_mask; int best_cpu; - cpus_and(domain_mask, sd->span, *lowest_mask); + cpumask_and(&domain_mask, sched_domain_span(sd), + lowest_mask); best_cpu = pick_optimal_cpu(this_cpu, &domain_mask); @@ -1057,8 +1060,8 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) * Also make sure that it wasn't scheduled on its rq. */ if (unlikely(task_rq(task) != rq || - !cpu_isset(lowest_rq->cpu, - task->cpus_allowed) || + !cpumask_test_cpu(lowest_rq->cpu, + &task->cpus_allowed) || task_running(rq, task) || !task->se.on_rq)) { @@ -1179,7 +1182,7 @@ static int pull_rt_task(struct rq *this_rq) next = pick_next_task_rt(this_rq); - for_each_cpu_mask_nr(cpu, this_rq->rd->rto_mask) { + for_each_cpu(cpu, this_rq->rd->rto_mask) { if (this_cpu == cpu) continue; @@ -1308,9 +1311,9 @@ move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest, } static void set_cpus_allowed_rt(struct task_struct *p, - const cpumask_t *new_mask) + const struct cpumask *new_mask) { - int weight = cpus_weight(*new_mask); + int weight = cpumask_weight(new_mask); BUG_ON(!rt_task(p)); @@ -1331,7 +1334,7 @@ static void set_cpus_allowed_rt(struct task_struct *p, update_rt_migration(rq); } - p->cpus_allowed = *new_mask; + cpumask_copy(&p->cpus_allowed, new_mask); p->rt.nr_cpus_allowed = weight; } @@ -1374,6 +1377,15 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p, if (!rq->rt.rt_nr_running) pull_rt_task(rq); } + +static inline void init_sched_rt_class(void) +{ + unsigned int i; + + for_each_possible_cpu(i) + alloc_cpumask_var_node(&per_cpu(local_cpu_mask, i), + GFP_KERNEL, cpu_to_node(i)); +} #endif /* CONFIG_SMP */ /* @@ -1544,3 +1556,4 @@ static void print_rt_stats(struct seq_file *m, int cpu) rcu_read_unlock(); } #endif /* CONFIG_SCHED_DEBUG */ + diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 7dbf72a..f2773b5 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -31,7 +31,7 @@ static int show_schedstat(struct seq_file *seq, void *v) rq->yld_act_empty, rq->yld_exp_empty, rq->yld_count, rq->sched_switch, rq->sched_count, rq->sched_goidle, rq->ttwu_count, rq->ttwu_local, - rq->rq_sched_info.cpu_time, + rq->rq_cpu_time, rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount); seq_printf(seq, "\n"); @@ -42,7 +42,8 @@ static int show_schedstat(struct seq_file *seq, void *v) for_each_domain(cpu, sd) { enum cpu_idle_type itype; - cpumask_scnprintf(mask_str, mask_len, sd->span); + cpumask_scnprintf(mask_str, mask_len, + sched_domain_span(sd)); seq_printf(seq, "domain%d %s", dcount++, mask_str); for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES; itype++) { @@ -123,7 +124,7 @@ static inline void rq_sched_info_depart(struct rq *rq, unsigned long long delta) { if (rq) - rq->rq_sched_info.cpu_time += delta; + rq->rq_cpu_time += delta; } static inline void @@ -236,7 +237,6 @@ static inline void sched_info_depart(struct task_struct *t) unsigned long long delta = task_rq(t)->clock - t->sched_info.last_arrival; - t->sched_info.cpu_time += delta; rq_sched_info_depart(task_rq(t), delta); if (t->state == TASK_RUNNING) diff --git a/kernel/signal.c b/kernel/signal.c index 4530fc6..3152ac3 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -41,6 +41,8 @@ static struct kmem_cache *sigqueue_cachep; +DEFINE_TRACE(sched_signal_send); + static void __user *sig_handler(struct task_struct *t, int sig) { return t->sighand->action[sig - 1].sa.sa_handler; @@ -177,6 +179,11 @@ int next_signal(struct sigpending *pending, sigset_t *mask) return sig; } +/* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appopriate lock must be held to stop the target task from exiting + */ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, int override_rlimit) { @@ -184,11 +191,12 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, struct user_struct *user; /* - * In order to avoid problems with "switch_user()", we want to make - * sure that the compiler doesn't re-load "t->user" + * We won't get problems with the target's UID changing under us + * because changing it requires RCU be used, and if t != current, the + * caller must be holding the RCU readlock (by way of a spinlock) and + * we use RCU protection here */ - user = t->user; - barrier(); + user = get_uid(__task_cred(t)->user); atomic_inc(&user->sigpending); if (override_rlimit || atomic_read(&user->sigpending) <= @@ -196,12 +204,14 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, q = kmem_cache_alloc(sigqueue_cachep, flags); if (unlikely(q == NULL)) { atomic_dec(&user->sigpending); + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; - q->user = get_uid(user); + q->user = user; } - return(q); + + return q; } static void __sigqueue_free(struct sigqueue *q) @@ -562,10 +572,12 @@ static int rm_from_queue(unsigned long mask, struct sigpending *s) /* * Bad permissions for sending the signal + * - the caller must hold at least the RCU read lock */ static int check_kill_permission(int sig, struct siginfo *info, struct task_struct *t) { + const struct cred *cred = current_cred(), *tcred; struct pid *sid; int error; @@ -579,8 +591,11 @@ static int check_kill_permission(int sig, struct siginfo *info, if (error) return error; - if ((current->euid ^ t->suid) && (current->euid ^ t->uid) && - (current->uid ^ t->suid) && (current->uid ^ t->uid) && + tcred = __task_cred(t); + if ((cred->euid ^ tcred->suid) && + (cred->euid ^ tcred->uid) && + (cred->uid ^ tcred->suid) && + (cred->uid ^ tcred->uid) && !capable(CAP_KILL)) { switch (sig) { case SIGCONT: @@ -843,8 +858,9 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, q->info.si_signo = sig; q->info.si_errno = 0; q->info.si_code = SI_USER; - q->info.si_pid = task_pid_vnr(current); - q->info.si_uid = current->uid; + q->info.si_pid = task_tgid_nr_ns(current, + task_active_pid_ns(t)); + q->info.si_uid = current_uid(); break; case (unsigned long) SEND_SIG_PRIV: q->info.si_signo = sig; @@ -1008,6 +1024,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long return sighand; } +/* + * send signal info to all the members of a group + * - the caller must hold the RCU read lock at least + */ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { unsigned long flags; @@ -1029,8 +1049,8 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) /* * __kill_pgrp_info() sends a signal to a process group: this is what the tty * control characters do (^C, ^Z etc) + * - the caller must hold at least a readlock on tasklist_lock */ - int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) { struct task_struct *p = NULL; @@ -1086,6 +1106,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, { int ret = -EINVAL; struct task_struct *p; + const struct cred *pcred; if (!valid_signal(sig)) return ret; @@ -1096,9 +1117,11 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, ret = -ESRCH; goto out_unlock; } - if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info))) - && (euid != p->suid) && (euid != p->uid) - && (uid != p->suid) && (uid != p->uid)) { + pcred = __task_cred(p); + if ((info == SEND_SIG_NOINFO || + (!is_si_special(info) && SI_FROMUSER(info))) && + euid != pcred->suid && euid != pcred->uid && + uid != pcred->suid && uid != pcred->uid) { ret = -EPERM; goto out_unlock; } @@ -1369,10 +1392,9 @@ int do_notify_parent(struct task_struct *tsk, int sig) */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns); + info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); - info.si_uid = tsk->uid; - thread_group_cputime(tsk, &cputime); info.si_utime = cputime_to_jiffies(cputime.utime); info.si_stime = cputime_to_jiffies(cputime.stime); @@ -1440,10 +1462,9 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns); + info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); - info.si_uid = tsk->uid; - info.si_utime = cputime_to_clock_t(tsk->utime); info.si_stime = cputime_to_clock_t(tsk->stime); @@ -1598,7 +1619,7 @@ void ptrace_notify(int exit_code) info.si_signo = SIGTRAP; info.si_code = exit_code; info.si_pid = task_pid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); /* Let the debugger run. */ spin_lock_irq(¤t->sighand->siglock); @@ -1710,7 +1731,7 @@ static int ptrace_signal(int signr, siginfo_t *info, info->si_errno = 0; info->si_code = SI_USER; info->si_pid = task_pid_vnr(current->parent); - info->si_uid = current->parent->uid; + info->si_uid = task_uid(current->parent); } /* If the (new) signal is now blocked, requeue it. */ @@ -2211,7 +2232,7 @@ sys_kill(pid_t pid, int sig) info.si_errno = 0; info.si_code = SI_USER; info.si_pid = task_tgid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); return kill_something_info(sig, &info, pid); } @@ -2228,7 +2249,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig) info.si_errno = 0; info.si_code = SI_TKILL; info.si_pid = task_tgid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); rcu_read_lock(); p = find_task_by_vpid(pid); diff --git a/kernel/smp.c b/kernel/smp.c index 75c8dde..5cfa0e5 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -24,8 +24,8 @@ struct call_function_data { struct call_single_data csd; spinlock_t lock; unsigned int refs; - cpumask_t cpumask; struct rcu_head rcu_head; + unsigned long cpumask_bits[]; }; struct call_single_queue { @@ -110,13 +110,13 @@ void generic_smp_call_function_interrupt(void) list_for_each_entry_rcu(data, &call_function_queue, csd.list) { int refs; - if (!cpu_isset(cpu, data->cpumask)) + if (!cpumask_test_cpu(cpu, to_cpumask(data->cpumask_bits))) continue; data->csd.func(data->csd.info); spin_lock(&data->lock); - cpu_clear(cpu, data->cpumask); + cpumask_clear_cpu(cpu, to_cpumask(data->cpumask_bits)); WARN_ON(data->refs == 0); data->refs--; refs = data->refs; @@ -223,7 +223,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, local_irq_save(flags); func(info); local_irq_restore(flags); - } else if ((unsigned)cpu < NR_CPUS && cpu_online(cpu)) { + } else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) { struct call_single_data *data = NULL; if (!wait) { @@ -266,51 +266,19 @@ void __smp_call_function_single(int cpu, struct call_single_data *data) generic_exec_single(cpu, data); } -/* Dummy function */ -static void quiesce_dummy(void *unused) -{ -} - -/* - * Ensure stack based data used in call function mask is safe to free. - * - * This is needed by smp_call_function_mask when using on-stack data, because - * a single call function queue is shared by all CPUs, and any CPU may pick up - * the data item on the queue at any time before it is deleted. So we need to - * ensure that all CPUs have transitioned through a quiescent state after - * this call. - * - * This is a very slow function, implemented by sending synchronous IPIs to - * all possible CPUs. For this reason, we have to alloc data rather than use - * stack based data even in the case of synchronous calls. The stack based - * data is then just used for deadlock/oom fallback which will be very rare. - * - * If a faster scheme can be made, we could go back to preferring stack based - * data -- the data allocation/free is non-zero cost. - */ -static void smp_call_function_mask_quiesce_stack(cpumask_t mask) -{ - struct call_single_data data; - int cpu; - - data.func = quiesce_dummy; - data.info = NULL; - - for_each_cpu_mask(cpu, mask) { - data.flags = CSD_FLAG_WAIT; - generic_exec_single(cpu, &data); - } -} +/* FIXME: Shim for archs using old arch_send_call_function_ipi API. */ +#ifndef arch_send_call_function_ipi_mask +#define arch_send_call_function_ipi_mask(maskp) \ + arch_send_call_function_ipi(*(maskp)) +#endif /** - * smp_call_function_mask(): Run a function on a set of other CPUs. - * @mask: The set of cpus to run on. + * smp_call_function_many(): Run a function on a set of other CPUs. + * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed on other CPUs. * - * Returns 0 on success, else a negative status code. - * * If @wait is true, then returns once @func has returned. Note that @wait * will be implicitly turned on in case of allocation failures, since * we fall back to on-stack allocation. @@ -319,53 +287,57 @@ static void smp_call_function_mask_quiesce_stack(cpumask_t mask) * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ -int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info, - int wait) +void smp_call_function_many(const struct cpumask *mask, + void (*func)(void *), void *info, + bool wait) { - struct call_function_data d; - struct call_function_data *data = NULL; - cpumask_t allbutself; + struct call_function_data *data; unsigned long flags; - int cpu, num_cpus; - int slowpath = 0; + int cpu, next_cpu; /* Can deadlock when called with interrupts disabled */ WARN_ON(irqs_disabled()); - cpu = smp_processor_id(); - allbutself = cpu_online_map; - cpu_clear(cpu, allbutself); - cpus_and(mask, mask, allbutself); - num_cpus = cpus_weight(mask); - - /* - * If zero CPUs, return. If just a single CPU, turn this request - * into a targetted single call instead since it's faster. - */ - if (!num_cpus) - return 0; - else if (num_cpus == 1) { - cpu = first_cpu(mask); - return smp_call_function_single(cpu, func, info, wait); + /* So, what's a CPU they want? Ignoring this one. */ + cpu = cpumask_first_and(mask, cpu_online_mask); + if (cpu == smp_processor_id()) + cpu = cpumask_next_and(cpu, mask, cpu_online_mask); + /* No online cpus? We're done. */ + if (cpu >= nr_cpu_ids) + return; + + /* Do we have another CPU which isn't us? */ + next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask); + if (next_cpu == smp_processor_id()) + next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask); + + /* Fastpath: do that cpu by itself. */ + if (next_cpu >= nr_cpu_ids) { + smp_call_function_single(cpu, func, info, wait); + return; } - data = kmalloc(sizeof(*data), GFP_ATOMIC); - if (data) { - data->csd.flags = CSD_FLAG_ALLOC; - if (wait) - data->csd.flags |= CSD_FLAG_WAIT; - } else { - data = &d; - data->csd.flags = CSD_FLAG_WAIT; - wait = 1; - slowpath = 1; + data = kmalloc(sizeof(*data) + cpumask_size(), GFP_ATOMIC); + if (unlikely(!data)) { + /* Slow path. */ + for_each_online_cpu(cpu) { + if (cpu == smp_processor_id()) + continue; + if (cpumask_test_cpu(cpu, mask)) + smp_call_function_single(cpu, func, info, wait); + } + return; } spin_lock_init(&data->lock); + data->csd.flags = CSD_FLAG_ALLOC; + if (wait) + data->csd.flags |= CSD_FLAG_WAIT; data->csd.func = func; data->csd.info = info; - data->refs = num_cpus; - data->cpumask = mask; + cpumask_and(to_cpumask(data->cpumask_bits), mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), to_cpumask(data->cpumask_bits)); + data->refs = cpumask_weight(to_cpumask(data->cpumask_bits)); spin_lock_irqsave(&call_function_lock, flags); list_add_tail_rcu(&data->csd.list, &call_function_queue); @@ -377,18 +349,13 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info, smp_mb(); /* Send a message to all CPUs in the map */ - arch_send_call_function_ipi(mask); + arch_send_call_function_ipi_mask(to_cpumask(data->cpumask_bits)); /* optionally wait for the CPUs to complete */ - if (wait) { + if (wait) csd_flag_wait(&data->csd); - if (unlikely(slowpath)) - smp_call_function_mask_quiesce_stack(mask); - } - - return 0; } -EXPORT_SYMBOL(smp_call_function_mask); +EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. @@ -396,7 +363,7 @@ EXPORT_SYMBOL(smp_call_function_mask); * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed on other CPUs. * - * Returns 0 on success, else a negative status code. + * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. In case of allocation @@ -407,12 +374,10 @@ EXPORT_SYMBOL(smp_call_function_mask); */ int smp_call_function(void (*func)(void *), void *info, int wait) { - int ret; - preempt_disable(); - ret = smp_call_function_mask(cpu_online_map, func, info, wait); + smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); - return ret; + return 0; } EXPORT_SYMBOL(smp_call_function); diff --git a/kernel/softirq.c b/kernel/softirq.c index e7c69a7..bdbe9de 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -102,20 +102,6 @@ void local_bh_disable(void) EXPORT_SYMBOL(local_bh_disable); -void __local_bh_enable(void) -{ - WARN_ON_ONCE(in_irq()); - - /* - * softirqs should never be enabled by __local_bh_enable(), - * it always nests inside local_bh_enable() sections: - */ - WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET); - - sub_preempt_count(SOFTIRQ_OFFSET); -} -EXPORT_SYMBOL_GPL(__local_bh_enable); - /* * Special-case - softirqs can safely be enabled in * cond_resched_softirq(), or by __do_softirq(), @@ -269,6 +255,7 @@ void irq_enter(void) { int cpu = smp_processor_id(); + rcu_irq_enter(); if (idle_cpu(cpu) && !in_interrupt()) { __irq_enter(); tick_check_idle(cpu); @@ -295,9 +282,9 @@ void irq_exit(void) #ifdef CONFIG_NO_HZ /* Make sure that timer wheel updates are propagated */ - if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched()) - tick_nohz_stop_sched_tick(0); rcu_irq_exit(); + if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) + tick_nohz_stop_sched_tick(0); #endif preempt_enable_no_resched(); } @@ -746,7 +733,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, break; /* Unbind so it can run. Fall thru. */ kthread_bind(per_cpu(ksoftirqd, hotcpu), - any_online_cpu(cpu_online_map)); + cpumask_any(cpu_online_mask)); case CPU_DEAD: case CPU_DEAD_FROZEN: { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; @@ -797,3 +784,23 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait) } EXPORT_SYMBOL(on_each_cpu); #endif + +/* + * [ These __weak aliases are kept in a separate compilation unit, so that + * GCC does not inline them incorrectly. ] + */ + +int __init __weak early_irq_init(void) +{ + return 0; +} + +int __init __weak arch_early_irq_init(void) +{ + return 0; +} + +int __weak arch_init_chip_data(struct irq_desc *desc, int cpu) +{ + return 0; +} diff --git a/kernel/softlockup.c b/kernel/softlockup.c index dc0b3be..d9188c6 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -164,7 +164,7 @@ unsigned long __read_mostly sysctl_hung_task_check_count = 1024; /* * Zero means infinite timeout - no checking done: */ -unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120; +unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480; unsigned long __read_mostly sysctl_hung_task_warnings = 10; @@ -303,17 +303,15 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - check_cpu = any_online_cpu(cpu_online_map); + check_cpu = cpumask_any(cpu_online_mask); wake_up_process(per_cpu(watchdog_task, hotcpu)); break; #ifdef CONFIG_HOTPLUG_CPU case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: if (hotcpu == check_cpu) { - cpumask_t temp_cpu_online_map = cpu_online_map; - - cpu_clear(hotcpu, temp_cpu_online_map); - check_cpu = any_online_cpu(temp_cpu_online_map); + /* Pick any other online cpu. */ + check_cpu = cpumask_any_but(cpu_online_mask, hotcpu); } break; @@ -323,7 +321,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; /* Unbind so it can run. Fall thru. */ kthread_bind(per_cpu(watchdog_task, hotcpu), - any_online_cpu(cpu_online_map)); + cpumask_any(cpu_online_mask)); case CPU_DEAD: case CPU_DEAD_FROZEN: p = per_cpu(watchdog_task, hotcpu); diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 94b527e..eb212f8 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -6,6 +6,7 @@ * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ #include <linux/sched.h> +#include <linux/kernel.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> @@ -24,3 +25,13 @@ void print_stack_trace(struct stack_trace *trace, int spaces) } EXPORT_SYMBOL_GPL(print_stack_trace); +/* + * Architectures that do not implement save_stack_trace_tsk get this + * weak alias and a once-per-bootup warning (whenever this facility + * is utilized - for example by procfs): + */ +__weak void +save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + WARN_ONCE(1, KERN_INFO "save_stack_trace_tsk() not implemented yet.\n"); +} diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 24e8cea..0cd415e 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -38,7 +38,10 @@ struct stop_machine_data { static unsigned int num_threads; static atomic_t thread_ack; static DEFINE_MUTEX(lock); - +/* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */ +static DEFINE_MUTEX(setup_lock); +/* Users of stop_machine. */ +static int refcount; static struct workqueue_struct *stop_machine_wq; static struct stop_machine_data active, idle; static const cpumask_t *active_cpus; @@ -69,10 +72,10 @@ static void stop_cpu(struct work_struct *unused) int err; if (!active_cpus) { - if (cpu == first_cpu(cpu_online_map)) + if (cpu == cpumask_first(cpu_online_mask)) smdata = &active; } else { - if (cpu_isset(cpu, *active_cpus)) + if (cpumask_test_cpu(cpu, active_cpus)) smdata = &active; } /* Simple state machine */ @@ -109,7 +112,44 @@ static int chill(void *unused) return 0; } -int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) +int stop_machine_create(void) +{ + mutex_lock(&setup_lock); + if (refcount) + goto done; + stop_machine_wq = create_rt_workqueue("kstop"); + if (!stop_machine_wq) + goto err_out; + stop_machine_work = alloc_percpu(struct work_struct); + if (!stop_machine_work) + goto err_out; +done: + refcount++; + mutex_unlock(&setup_lock); + return 0; + +err_out: + if (stop_machine_wq) + destroy_workqueue(stop_machine_wq); + mutex_unlock(&setup_lock); + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(stop_machine_create); + +void stop_machine_destroy(void) +{ + mutex_lock(&setup_lock); + refcount--; + if (refcount) + goto done; + destroy_workqueue(stop_machine_wq); + free_percpu(stop_machine_work); +done: + mutex_unlock(&setup_lock); +} +EXPORT_SYMBOL_GPL(stop_machine_destroy); + +int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) { struct work_struct *sm_work; int i, ret; @@ -142,23 +182,18 @@ int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) return ret; } -int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus) +int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) { int ret; + ret = stop_machine_create(); + if (ret) + return ret; /* No CPUs can come up or down during this. */ get_online_cpus(); ret = __stop_machine(fn, data, cpus); put_online_cpus(); - + stop_machine_destroy(); return ret; } EXPORT_SYMBOL_GPL(stop_machine); - -static int __init stop_machine_init(void) -{ - stop_machine_wq = create_rt_workqueue("kstop"); - stop_machine_work = alloc_percpu(struct work_struct); - return 0; -} -core_initcall(stop_machine_init); diff --git a/kernel/sys.c b/kernel/sys.c index 31deba8..763c3c1 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -33,6 +33,7 @@ #include <linux/task_io_accounting_ops.h> #include <linux/seccomp.h> #include <linux/cpu.h> +#include <linux/ptrace.h> #include <linux/compat.h> #include <linux/syscalls.h> @@ -112,12 +113,17 @@ EXPORT_SYMBOL(cad_pid); void (*pm_power_off_prepare)(void); +/* + * set the priority of a task + * - the caller must hold the RCU read lock + */ static int set_one_prio(struct task_struct *p, int niceval, int error) { + const struct cred *cred = current_cred(), *pcred = __task_cred(p); int no_nice; - if (p->uid != current->euid && - p->euid != current->euid && !capable(CAP_SYS_NICE)) { + if (pcred->uid != cred->euid && + pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) { error = -EPERM; goto out; } @@ -141,6 +147,7 @@ asmlinkage long sys_setpriority(int which, int who, int niceval) { struct task_struct *g, *p; struct user_struct *user; + const struct cred *cred = current_cred(); int error = -EINVAL; struct pid *pgrp; @@ -174,18 +181,18 @@ asmlinkage long sys_setpriority(int which, int who, int niceval) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - user = current->user; + user = (struct user_struct *) cred->user; if (!who) - who = current->uid; - else - if ((who != current->uid) && !(user = find_user(who))) - goto out_unlock; /* No processes for this user */ + who = cred->uid; + else if ((who != cred->uid) && + !(user = find_user(who))) + goto out_unlock; /* No processes for this user */ do_each_thread(g, p) - if (p->uid == who) + if (__task_cred(p)->uid == who) error = set_one_prio(p, niceval, error); while_each_thread(g, p); - if (who != current->uid) + if (who != cred->uid) free_uid(user); /* For find_user() */ break; } @@ -205,6 +212,7 @@ asmlinkage long sys_getpriority(int which, int who) { struct task_struct *g, *p; struct user_struct *user; + const struct cred *cred = current_cred(); long niceval, retval = -ESRCH; struct pid *pgrp; @@ -236,21 +244,21 @@ asmlinkage long sys_getpriority(int which, int who) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - user = current->user; + user = (struct user_struct *) cred->user; if (!who) - who = current->uid; - else - if ((who != current->uid) && !(user = find_user(who))) - goto out_unlock; /* No processes for this user */ + who = cred->uid; + else if ((who != cred->uid) && + !(user = find_user(who))) + goto out_unlock; /* No processes for this user */ do_each_thread(g, p) - if (p->uid == who) { + if (__task_cred(p)->uid == who) { niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; } while_each_thread(g, p); - if (who != current->uid) + if (who != cred->uid) free_uid(user); /* for find_user() */ break; } @@ -472,46 +480,48 @@ void ctrl_alt_del(void) */ asmlinkage long sys_setregid(gid_t rgid, gid_t egid) { - int old_rgid = current->gid; - int old_egid = current->egid; - int new_rgid = old_rgid; - int new_egid = old_egid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE); if (retval) - return retval; + goto error; + retval = -EPERM; if (rgid != (gid_t) -1) { - if ((old_rgid == rgid) || - (current->egid==rgid) || + if (old->gid == rgid || + old->egid == rgid || capable(CAP_SETGID)) - new_rgid = rgid; + new->gid = rgid; else - return -EPERM; + goto error; } if (egid != (gid_t) -1) { - if ((old_rgid == egid) || - (current->egid == egid) || - (current->sgid == egid) || + if (old->gid == egid || + old->egid == egid || + old->sgid == egid || capable(CAP_SETGID)) - new_egid = egid; + new->egid = egid; else - return -EPERM; - } - if (new_egid != old_egid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); + goto error; } + if (rgid != (gid_t) -1 || - (egid != (gid_t) -1 && egid != old_rgid)) - current->sgid = new_egid; - current->fsgid = new_egid; - current->egid = new_egid; - current->gid = new_rgid; - key_fsgid_changed(current); - proc_id_connector(current, PROC_EVENT_GID); - return 0; + (egid != (gid_t) -1 && egid != old->gid)) + new->sgid = new->egid; + new->fsgid = new->egid; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; } /* @@ -521,56 +531,54 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid) */ asmlinkage long sys_setgid(gid_t gid) { - int old_egid = current->egid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID); if (retval) - return retval; + goto error; - if (capable(CAP_SETGID)) { - if (old_egid != gid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->gid = current->egid = current->sgid = current->fsgid = gid; - } else if ((gid == current->gid) || (gid == current->sgid)) { - if (old_egid != gid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->egid = current->fsgid = gid; - } + retval = -EPERM; + if (capable(CAP_SETGID)) + new->gid = new->egid = new->sgid = new->fsgid = gid; + else if (gid == old->gid || gid == old->sgid) + new->egid = new->fsgid = gid; else - return -EPERM; + goto error; - key_fsgid_changed(current); - proc_id_connector(current, PROC_EVENT_GID); - return 0; + return commit_creds(new); + +error: + abort_creds(new); + return retval; } -static int set_user(uid_t new_ruid, int dumpclear) +/* + * change the user struct in a credentials set to match the new UID + */ +static int set_user(struct cred *new) { struct user_struct *new_user; - new_user = alloc_uid(current->nsproxy->user_ns, new_ruid); + new_user = alloc_uid(current_user_ns(), new->uid); if (!new_user) return -EAGAIN; if (atomic_read(&new_user->processes) >= current->signal->rlim[RLIMIT_NPROC].rlim_cur && - new_user != current->nsproxy->user_ns->root_user) { + new_user != INIT_USER) { free_uid(new_user); return -EAGAIN; } - switch_uid(new_user); - - if (dumpclear) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->uid = new_ruid; + free_uid(new->user); + new->user = new_user; return 0; } @@ -591,54 +599,56 @@ static int set_user(uid_t new_ruid, int dumpclear) */ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) { - int old_ruid, old_euid, old_suid, new_ruid, new_euid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE); if (retval) - return retval; - - new_ruid = old_ruid = current->uid; - new_euid = old_euid = current->euid; - old_suid = current->suid; + goto error; + retval = -EPERM; if (ruid != (uid_t) -1) { - new_ruid = ruid; - if ((old_ruid != ruid) && - (current->euid != ruid) && + new->uid = ruid; + if (old->uid != ruid && + old->euid != ruid && !capable(CAP_SETUID)) - return -EPERM; + goto error; } if (euid != (uid_t) -1) { - new_euid = euid; - if ((old_ruid != euid) && - (current->euid != euid) && - (current->suid != euid) && + new->euid = euid; + if (old->uid != euid && + old->euid != euid && + old->suid != euid && !capable(CAP_SETUID)) - return -EPERM; + goto error; } - if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0) - return -EAGAIN; + retval = -EAGAIN; + if (new->uid != old->uid && set_user(new) < 0) + goto error; - if (new_euid != old_euid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->fsuid = current->euid = new_euid; if (ruid != (uid_t) -1 || - (euid != (uid_t) -1 && euid != old_ruid)) - current->suid = current->euid; - current->fsuid = current->euid; + (euid != (uid_t) -1 && euid != old->uid)) + new->suid = new->euid; + new->fsuid = new->euid; - key_fsuid_changed(current); - proc_id_connector(current, PROC_EVENT_UID); - - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE); -} + retval = security_task_fix_setuid(new, old, LSM_SETID_RE); + if (retval < 0) + goto error; + return commit_creds(new); +error: + abort_creds(new); + return retval; +} /* * setuid() is implemented like SysV with SAVED_IDS @@ -653,36 +663,41 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) */ asmlinkage long sys_setuid(uid_t uid) { - int old_euid = current->euid; - int old_ruid, old_suid, new_suid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID); if (retval) - return retval; + goto error; - old_ruid = current->uid; - old_suid = current->suid; - new_suid = old_suid; - + retval = -EPERM; if (capable(CAP_SETUID)) { - if (uid != old_ruid && set_user(uid, old_euid != uid) < 0) - return -EAGAIN; - new_suid = uid; - } else if ((uid != current->uid) && (uid != new_suid)) - return -EPERM; - - if (old_euid != uid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); + new->suid = new->uid = uid; + if (uid != old->uid && set_user(new) < 0) { + retval = -EAGAIN; + goto error; + } + } else if (uid != old->uid && uid != new->suid) { + goto error; } - current->fsuid = current->euid = uid; - current->suid = new_suid; - key_fsuid_changed(current); - proc_id_connector(current, PROC_EVENT_UID); + new->fsuid = new->euid = uid; + + retval = security_task_fix_setuid(new, old, LSM_SETID_ID); + if (retval < 0) + goto error; - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID); + return commit_creds(new); + +error: + abort_creds(new); + return retval; } @@ -692,54 +707,63 @@ asmlinkage long sys_setuid(uid_t uid) */ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) { - int old_ruid = current->uid; - int old_euid = current->euid; - int old_suid = current->suid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES); if (retval) - return retval; + goto error; + old = current_cred(); + retval = -EPERM; if (!capable(CAP_SETUID)) { - if ((ruid != (uid_t) -1) && (ruid != current->uid) && - (ruid != current->euid) && (ruid != current->suid)) - return -EPERM; - if ((euid != (uid_t) -1) && (euid != current->uid) && - (euid != current->euid) && (euid != current->suid)) - return -EPERM; - if ((suid != (uid_t) -1) && (suid != current->uid) && - (suid != current->euid) && (suid != current->suid)) - return -EPERM; + if (ruid != (uid_t) -1 && ruid != old->uid && + ruid != old->euid && ruid != old->suid) + goto error; + if (euid != (uid_t) -1 && euid != old->uid && + euid != old->euid && euid != old->suid) + goto error; + if (suid != (uid_t) -1 && suid != old->uid && + suid != old->euid && suid != old->suid) + goto error; } + + retval = -EAGAIN; if (ruid != (uid_t) -1) { - if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0) - return -EAGAIN; + new->uid = ruid; + if (ruid != old->uid && set_user(new) < 0) + goto error; } - if (euid != (uid_t) -1) { - if (euid != current->euid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->euid = euid; - } - current->fsuid = current->euid; + if (euid != (uid_t) -1) + new->euid = euid; if (suid != (uid_t) -1) - current->suid = suid; + new->suid = suid; + new->fsuid = new->euid; + + retval = security_task_fix_setuid(new, old, LSM_SETID_RES); + if (retval < 0) + goto error; - key_fsuid_changed(current); - proc_id_connector(current, PROC_EVENT_UID); + return commit_creds(new); - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES); +error: + abort_creds(new); + return retval; } asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(current->uid, ruid)) && - !(retval = put_user(current->euid, euid))) - retval = put_user(current->suid, suid); + if (!(retval = put_user(cred->uid, ruid)) && + !(retval = put_user(cred->euid, euid))) + retval = put_user(cred->suid, suid); return retval; } @@ -749,48 +773,55 @@ asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __us */ asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) { + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES); if (retval) - return retval; + goto error; + retval = -EPERM; if (!capable(CAP_SETGID)) { - if ((rgid != (gid_t) -1) && (rgid != current->gid) && - (rgid != current->egid) && (rgid != current->sgid)) - return -EPERM; - if ((egid != (gid_t) -1) && (egid != current->gid) && - (egid != current->egid) && (egid != current->sgid)) - return -EPERM; - if ((sgid != (gid_t) -1) && (sgid != current->gid) && - (sgid != current->egid) && (sgid != current->sgid)) - return -EPERM; - } - if (egid != (gid_t) -1) { - if (egid != current->egid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->egid = egid; + if (rgid != (gid_t) -1 && rgid != old->gid && + rgid != old->egid && rgid != old->sgid) + goto error; + if (egid != (gid_t) -1 && egid != old->gid && + egid != old->egid && egid != old->sgid) + goto error; + if (sgid != (gid_t) -1 && sgid != old->gid && + sgid != old->egid && sgid != old->sgid) + goto error; } - current->fsgid = current->egid; + if (rgid != (gid_t) -1) - current->gid = rgid; + new->gid = rgid; + if (egid != (gid_t) -1) + new->egid = egid; if (sgid != (gid_t) -1) - current->sgid = sgid; + new->sgid = sgid; + new->fsgid = new->egid; - key_fsgid_changed(current); - proc_id_connector(current, PROC_EVENT_GID); - return 0; + return commit_creds(new); + +error: + abort_creds(new); + return retval; } asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(current->gid, rgid)) && - !(retval = put_user(current->egid, egid))) - retval = put_user(current->sgid, sgid); + if (!(retval = put_user(cred->gid, rgid)) && + !(retval = put_user(cred->egid, egid))) + retval = put_user(cred->sgid, sgid); return retval; } @@ -804,27 +835,35 @@ asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __us */ asmlinkage long sys_setfsuid(uid_t uid) { - int old_fsuid; + const struct cred *old; + struct cred *new; + uid_t old_fsuid; + + new = prepare_creds(); + if (!new) + return current_fsuid(); + old = current_cred(); + old_fsuid = old->fsuid; - old_fsuid = current->fsuid; - if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS)) - return old_fsuid; + if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0) + goto error; - if (uid == current->uid || uid == current->euid || - uid == current->suid || uid == current->fsuid || + if (uid == old->uid || uid == old->euid || + uid == old->suid || uid == old->fsuid || capable(CAP_SETUID)) { if (uid != old_fsuid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); + new->fsuid = uid; + if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) + goto change_okay; } - current->fsuid = uid; } - key_fsuid_changed(current); - proc_id_connector(current, PROC_EVENT_UID); - - security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS); +error: + abort_creds(new); + return old_fsuid; +change_okay: + commit_creds(new); return old_fsuid; } @@ -833,23 +872,34 @@ asmlinkage long sys_setfsuid(uid_t uid) */ asmlinkage long sys_setfsgid(gid_t gid) { - int old_fsgid; + const struct cred *old; + struct cred *new; + gid_t old_fsgid; + + new = prepare_creds(); + if (!new) + return current_fsgid(); + old = current_cred(); + old_fsgid = old->fsgid; - old_fsgid = current->fsgid; if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS)) - return old_fsgid; + goto error; - if (gid == current->gid || gid == current->egid || - gid == current->sgid || gid == current->fsgid || + if (gid == old->gid || gid == old->egid || + gid == old->sgid || gid == old->fsgid || capable(CAP_SETGID)) { if (gid != old_fsgid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); + new->fsgid = gid; + goto change_okay; } - current->fsgid = gid; - key_fsgid_changed(current); - proc_id_connector(current, PROC_EVENT_GID); } + +error: + abort_creds(new); + return old_fsgid; + +change_okay: + commit_creds(new); return old_fsgid; } @@ -858,8 +908,8 @@ void do_sys_times(struct tms *tms) struct task_cputime cputime; cputime_t cutime, cstime; - spin_lock_irq(¤t->sighand->siglock); thread_group_cputime(current, &cputime); + spin_lock_irq(¤t->sighand->siglock); cutime = current->signal->cutime; cstime = current->signal->cstime; spin_unlock_irq(¤t->sighand->siglock); @@ -878,6 +928,7 @@ asmlinkage long sys_times(struct tms __user * tbuf) if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } + force_successful_syscall_return(); return (long) jiffies_64_to_clock_t(get_jiffies_64()); } @@ -1118,7 +1169,7 @@ EXPORT_SYMBOL(groups_free); /* export the group_info to a user-space array */ static int groups_to_user(gid_t __user *grouplist, - struct group_info *group_info) + const struct group_info *group_info) { int i; unsigned int count = group_info->ngroups; @@ -1186,7 +1237,7 @@ static void groups_sort(struct group_info *group_info) } /* a simple bsearch */ -int groups_search(struct group_info *group_info, gid_t grp) +int groups_search(const struct group_info *group_info, gid_t grp) { unsigned int left, right; @@ -1208,51 +1259,74 @@ int groups_search(struct group_info *group_info, gid_t grp) return 0; } -/* validate and set current->group_info */ -int set_current_groups(struct group_info *group_info) +/** + * set_groups - Change a group subscription in a set of credentials + * @new: The newly prepared set of credentials to alter + * @group_info: The group list to install + * + * Validate a group subscription and, if valid, insert it into a set + * of credentials. + */ +int set_groups(struct cred *new, struct group_info *group_info) { int retval; - struct group_info *old_info; retval = security_task_setgroups(group_info); if (retval) return retval; + put_group_info(new->group_info); groups_sort(group_info); get_group_info(group_info); + new->group_info = group_info; + return 0; +} - task_lock(current); - old_info = current->group_info; - current->group_info = group_info; - task_unlock(current); +EXPORT_SYMBOL(set_groups); - put_group_info(old_info); +/** + * set_current_groups - Change current's group subscription + * @group_info: The group list to impose + * + * Validate a group subscription and, if valid, impose it upon current's task + * security record. + */ +int set_current_groups(struct group_info *group_info) +{ + struct cred *new; + int ret; - return 0; + new = prepare_creds(); + if (!new) + return -ENOMEM; + + ret = set_groups(new, group_info); + if (ret < 0) { + abort_creds(new); + return ret; + } + + return commit_creds(new); } EXPORT_SYMBOL(set_current_groups); asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist) { - int i = 0; - - /* - * SMP: Nobody else can change our grouplist. Thus we are - * safe. - */ + const struct cred *cred = current_cred(); + int i; if (gidsetsize < 0) return -EINVAL; /* no need to grab task_lock here; it cannot change */ - i = current->group_info->ngroups; + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups_to_user(grouplist, current->group_info)) { + if (groups_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } @@ -1296,9 +1370,11 @@ asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist) */ int in_group_p(gid_t grp) { + const struct cred *cred = current_cred(); int retval = 1; - if (grp != current->fsgid) - retval = groups_search(current->group_info, grp); + + if (grp != cred->fsgid) + retval = groups_search(cred->group_info, grp); return retval; } @@ -1306,9 +1382,11 @@ EXPORT_SYMBOL(in_group_p); int in_egroup_p(gid_t grp) { + const struct cred *cred = current_cred(); int retval = 1; - if (grp != current->egid) - retval = groups_search(current->group_info, grp); + + if (grp != cred->egid) + retval = groups_search(cred->group_info, grp); return retval; } @@ -1551,6 +1629,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) utime = stime = cputime_zero; if (who == RUSAGE_THREAD) { + utime = task_utime(current); + stime = task_stime(current); accumulate_thread_rusage(p, r); goto out; } @@ -1624,50 +1704,56 @@ asmlinkage long sys_umask(int mask) asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { - long error = 0; + struct task_struct *me = current; + unsigned char comm[sizeof(me->comm)]; + long error; - if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error)) + error = security_task_prctl(option, arg2, arg3, arg4, arg5); + if (error != -ENOSYS) return error; + error = 0; switch (option) { case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; break; } - current->pdeath_signal = arg2; + me->pdeath_signal = arg2; + error = 0; break; case PR_GET_PDEATHSIG: - error = put_user(current->pdeath_signal, (int __user *)arg2); + error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: - error = get_dumpable(current->mm); + error = get_dumpable(me->mm); break; case PR_SET_DUMPABLE: if (arg2 < 0 || arg2 > 1) { error = -EINVAL; break; } - set_dumpable(current->mm, arg2); + set_dumpable(me->mm, arg2); + error = 0; break; case PR_SET_UNALIGN: - error = SET_UNALIGN_CTL(current, arg2); + error = SET_UNALIGN_CTL(me, arg2); break; case PR_GET_UNALIGN: - error = GET_UNALIGN_CTL(current, arg2); + error = GET_UNALIGN_CTL(me, arg2); break; case PR_SET_FPEMU: - error = SET_FPEMU_CTL(current, arg2); + error = SET_FPEMU_CTL(me, arg2); break; case PR_GET_FPEMU: - error = GET_FPEMU_CTL(current, arg2); + error = GET_FPEMU_CTL(me, arg2); break; case PR_SET_FPEXC: - error = SET_FPEXC_CTL(current, arg2); + error = SET_FPEXC_CTL(me, arg2); break; case PR_GET_FPEXC: - error = GET_FPEXC_CTL(current, arg2); + error = GET_FPEXC_CTL(me, arg2); break; case PR_GET_TIMING: error = PR_TIMING_STATISTICAL; @@ -1675,33 +1761,28 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, case PR_SET_TIMING: if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; + else + error = 0; break; - case PR_SET_NAME: { - struct task_struct *me = current; - unsigned char ncomm[sizeof(me->comm)]; - - ncomm[sizeof(me->comm)-1] = 0; - if (strncpy_from_user(ncomm, (char __user *)arg2, - sizeof(me->comm)-1) < 0) + case PR_SET_NAME: + comm[sizeof(me->comm)-1] = 0; + if (strncpy_from_user(comm, (char __user *)arg2, + sizeof(me->comm) - 1) < 0) return -EFAULT; - set_task_comm(me, ncomm); + set_task_comm(me, comm); return 0; - } - case PR_GET_NAME: { - struct task_struct *me = current; - unsigned char tcomm[sizeof(me->comm)]; - - get_task_comm(tcomm, me); - if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm))) + case PR_GET_NAME: + get_task_comm(comm, me); + if (copy_to_user((char __user *)arg2, comm, + sizeof(comm))) return -EFAULT; return 0; - } case PR_GET_ENDIAN: - error = GET_ENDIAN(current, arg2); + error = GET_ENDIAN(me, arg2); break; case PR_SET_ENDIAN: - error = SET_ENDIAN(current, arg2); + error = SET_ENDIAN(me, arg2); break; case PR_GET_SECCOMP: @@ -1725,6 +1806,7 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, current->default_timer_slack_ns; else current->timer_slack_ns = arg2; + error = 0; break; default: error = -EINVAL; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3d56fe7..92f6e5b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -87,10 +87,6 @@ extern int rcutorture_runnable; #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ /* Constants used for minimum and maximum */ -#if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP) -static int one = 1; -#endif - #ifdef CONFIG_DETECT_SOFTLOCKUP static int sixty = 60; static int neg_one = -1; @@ -101,6 +97,7 @@ static int two = 2; #endif static int zero; +static int one = 1; static int one_hundred = 100; /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ @@ -121,6 +118,10 @@ extern int sg_big_buff; #include <asm/system.h> #endif +#ifdef CONFIG_SPARC64 +extern int sysctl_tsb_ratio; +#endif + #ifdef __hppa__ extern int pwrsw_enabled; extern int unaligned_enabled; @@ -451,6 +452,16 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif +#ifdef CONFIG_SPARC64 + { + .ctl_name = CTL_UNNUMBERED, + .procname = "tsb-ratio", + .data = &sysctl_tsb_ratio, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif #ifdef __hppa__ { .ctl_name = KERN_HPPA_PWRSW, @@ -487,6 +498,26 @@ static struct ctl_table kern_table[] = { .proc_handler = &ftrace_enable_sysctl, }, #endif +#ifdef CONFIG_STACK_TRACER + { + .ctl_name = CTL_UNNUMBERED, + .procname = "stack_tracer_enabled", + .data = &stack_tracer_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &stack_trace_sysctl, + }, +#endif +#ifdef CONFIG_TRACING + { + .ctl_name = CTL_UNNUMBERED, + .procname = "ftrace_dump_on_oops", + .data = &ftrace_dump_on_oops, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif #ifdef CONFIG_MODULES { .ctl_name = KERN_MODPROBE, @@ -918,12 +949,22 @@ static struct ctl_table vm_table[] = { .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = &dirty_background_ratio_handler, .strategy = &sysctl_intvec, .extra1 = &zero, .extra2 = &one_hundred, }, { + .ctl_name = CTL_UNNUMBERED, + .procname = "dirty_background_bytes", + .data = &dirty_background_bytes, + .maxlen = sizeof(dirty_background_bytes), + .mode = 0644, + .proc_handler = &dirty_background_bytes_handler, + .strategy = &sysctl_intvec, + .extra1 = &one, + }, + { .ctl_name = VM_DIRTY_RATIO, .procname = "dirty_ratio", .data = &vm_dirty_ratio, @@ -935,6 +976,16 @@ static struct ctl_table vm_table[] = { .extra2 = &one_hundred, }, { + .ctl_name = CTL_UNNUMBERED, + .procname = "dirty_bytes", + .data = &vm_dirty_bytes, + .maxlen = sizeof(vm_dirty_bytes), + .mode = 0644, + .proc_handler = &dirty_bytes_handler, + .strategy = &sysctl_intvec, + .extra1 = &one, + }, + { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), @@ -1651,7 +1702,7 @@ out: static int test_perm(int mode, int op) { - if (!current->euid) + if (!current_euid()) mode >>= 6; else if (in_egroup_p(0)) mode >>= 3; diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c index c35da23a..fafeb48 100644 --- a/kernel/sysctl_check.c +++ b/kernel/sysctl_check.c @@ -730,7 +730,6 @@ static const struct trans_ctl_table trans_fs_quota_table[] = { }; static const struct trans_ctl_table trans_fs_xfs_table[] = { - { XFS_RESTRICT_CHOWN, "restrict_chown" }, { XFS_SGID_INHERIT, "irix_sgid_inherit" }, { XFS_SYMLINK_MODE, "irix_symlink_mode" }, { XFS_PANIC_MASK, "panic_mask" }, diff --git a/kernel/taskstats.c b/kernel/taskstats.c index bd6be76..888adbc 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -290,18 +290,17 @@ ret: return; } -static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd) +static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) { struct listener_list *listeners; struct listener *s, *tmp; unsigned int cpu; - cpumask_t mask = *maskp; - if (!cpus_subset(mask, cpu_possible_map)) + if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; if (isadd == REGISTER) { - for_each_cpu_mask_nr(cpu, mask) { + for_each_cpu(cpu, mask) { s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, cpu_to_node(cpu)); if (!s) @@ -320,7 +319,7 @@ static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd) /* Deregister or cleanup */ cleanup: - for_each_cpu_mask_nr(cpu, mask) { + for_each_cpu(cpu, mask) { listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); list_for_each_entry_safe(s, tmp, &listeners->list, list) { @@ -335,7 +334,7 @@ cleanup: return 0; } -static int parse(struct nlattr *na, cpumask_t *mask) +static int parse(struct nlattr *na, struct cpumask *mask) { char *data; int len; @@ -352,7 +351,7 @@ static int parse(struct nlattr *na, cpumask_t *mask) if (!data) return -ENOMEM; nla_strlcpy(data, na, len); - ret = cpulist_parse(data, *mask); + ret = cpulist_parse(data, mask); kfree(data); return ret; } @@ -428,23 +427,33 @@ err: static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) { - int rc = 0; + int rc; struct sk_buff *rep_skb; struct taskstats *stats; size_t size; - cpumask_t mask; + cpumask_var_t mask; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; - rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], &mask); + rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); if (rc < 0) - return rc; - if (rc == 0) - return add_del_listener(info->snd_pid, &mask, REGISTER); + goto free_return_rc; + if (rc == 0) { + rc = add_del_listener(info->snd_pid, mask, REGISTER); + goto free_return_rc; + } - rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], &mask); + rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); if (rc < 0) + goto free_return_rc; + if (rc == 0) { + rc = add_del_listener(info->snd_pid, mask, DEREGISTER); +free_return_rc: + free_cpumask_var(mask); return rc; - if (rc == 0) - return add_del_listener(info->snd_pid, &mask, DEREGISTER); + } + free_cpumask_var(mask); /* * Size includes space for nested attributes diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c index 06b6395..4f10451 100644 --- a/kernel/test_kprobes.c +++ b/kernel/test_kprobes.c @@ -22,21 +22,11 @@ static u32 rand1, preh_val, posth_val, jph_val; static int errors, handler_errors, num_tests; +static u32 (*target)(u32 value); +static u32 (*target2)(u32 value); static noinline u32 kprobe_target(u32 value) { - /* - * gcc ignores noinline on some architectures unless we stuff - * sufficient lard into the function. The get_kprobe() here is - * just for that. - * - * NOTE: We aren't concerned about the correctness of get_kprobe() - * here; hence, this call is neither under !preempt nor with the - * kprobe_mutex held. This is fine(tm) - */ - if (get_kprobe((void *)0xdeadbeef)) - printk(KERN_INFO "Kprobe smoke test: probe on 0xdeadbeef!\n"); - return (value / div_factor); } @@ -74,7 +64,7 @@ static int test_kprobe(void) return ret; } - ret = kprobe_target(rand1); + ret = target(rand1); unregister_kprobe(&kp); if (preh_val == 0) { @@ -92,6 +82,84 @@ static int test_kprobe(void) return 0; } +static noinline u32 kprobe_target2(u32 value) +{ + return (value / div_factor) + 1; +} + +static int kp_pre_handler2(struct kprobe *p, struct pt_regs *regs) +{ + preh_val = (rand1 / div_factor) + 1; + return 0; +} + +static void kp_post_handler2(struct kprobe *p, struct pt_regs *regs, + unsigned long flags) +{ + if (preh_val != (rand1 / div_factor) + 1) { + handler_errors++; + printk(KERN_ERR "Kprobe smoke test failed: " + "incorrect value in post_handler2\n"); + } + posth_val = preh_val + div_factor; +} + +static struct kprobe kp2 = { + .symbol_name = "kprobe_target2", + .pre_handler = kp_pre_handler2, + .post_handler = kp_post_handler2 +}; + +static int test_kprobes(void) +{ + int ret; + struct kprobe *kps[2] = {&kp, &kp2}; + + kp.addr = 0; /* addr should be cleard for reusing kprobe. */ + ret = register_kprobes(kps, 2); + if (ret < 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "register_kprobes returned %d\n", ret); + return ret; + } + + preh_val = 0; + posth_val = 0; + ret = target(rand1); + + if (preh_val == 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "kprobe pre_handler not called\n"); + handler_errors++; + } + + if (posth_val == 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "kprobe post_handler not called\n"); + handler_errors++; + } + + preh_val = 0; + posth_val = 0; + ret = target2(rand1); + + if (preh_val == 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "kprobe pre_handler2 not called\n"); + handler_errors++; + } + + if (posth_val == 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "kprobe post_handler2 not called\n"); + handler_errors++; + } + + unregister_kprobes(kps, 2); + return 0; + +} + static u32 j_kprobe_target(u32 value) { if (value != rand1) { @@ -121,7 +189,7 @@ static int test_jprobe(void) return ret; } - ret = kprobe_target(rand1); + ret = target(rand1); unregister_jprobe(&jp); if (jph_val == 0) { printk(KERN_ERR "Kprobe smoke test failed: " @@ -132,6 +200,43 @@ static int test_jprobe(void) return 0; } +static struct jprobe jp2 = { + .entry = j_kprobe_target, + .kp.symbol_name = "kprobe_target2" +}; + +static int test_jprobes(void) +{ + int ret; + struct jprobe *jps[2] = {&jp, &jp2}; + + jp.kp.addr = 0; /* addr should be cleard for reusing kprobe. */ + ret = register_jprobes(jps, 2); + if (ret < 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "register_jprobes returned %d\n", ret); + return ret; + } + + jph_val = 0; + ret = target(rand1); + if (jph_val == 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "jprobe handler not called\n"); + handler_errors++; + } + + jph_val = 0; + ret = target2(rand1); + if (jph_val == 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "jprobe handler2 not called\n"); + handler_errors++; + } + unregister_jprobes(jps, 2); + + return 0; +} #ifdef CONFIG_KRETPROBES static u32 krph_val; @@ -177,7 +282,7 @@ static int test_kretprobe(void) return ret; } - ret = kprobe_target(rand1); + ret = target(rand1); unregister_kretprobe(&rp); if (krph_val != rand1) { printk(KERN_ERR "Kprobe smoke test failed: " @@ -187,12 +292,72 @@ static int test_kretprobe(void) return 0; } + +static int return_handler2(struct kretprobe_instance *ri, struct pt_regs *regs) +{ + unsigned long ret = regs_return_value(regs); + + if (ret != (rand1 / div_factor) + 1) { + handler_errors++; + printk(KERN_ERR "Kprobe smoke test failed: " + "incorrect value in kretprobe handler2\n"); + } + if (krph_val == 0) { + handler_errors++; + printk(KERN_ERR "Kprobe smoke test failed: " + "call to kretprobe entry handler failed\n"); + } + + krph_val = rand1; + return 0; +} + +static struct kretprobe rp2 = { + .handler = return_handler2, + .entry_handler = entry_handler, + .kp.symbol_name = "kprobe_target2" +}; + +static int test_kretprobes(void) +{ + int ret; + struct kretprobe *rps[2] = {&rp, &rp2}; + + rp.kp.addr = 0; /* addr should be cleard for reusing kprobe. */ + ret = register_kretprobes(rps, 2); + if (ret < 0) { + printk(KERN_ERR "Kprobe smoke test failed: " + "register_kretprobe returned %d\n", ret); + return ret; + } + + krph_val = 0; + ret = target(rand1); + if (krph_val != rand1) { + printk(KERN_ERR "Kprobe smoke test failed: " + "kretprobe handler not called\n"); + handler_errors++; + } + + krph_val = 0; + ret = target2(rand1); + if (krph_val != rand1) { + printk(KERN_ERR "Kprobe smoke test failed: " + "kretprobe handler2 not called\n"); + handler_errors++; + } + unregister_kretprobes(rps, 2); + return 0; +} #endif /* CONFIG_KRETPROBES */ int init_test_probes(void) { int ret; + target = kprobe_target; + target2 = kprobe_target2; + do { rand1 = random32(); } while (rand1 <= div_factor); @@ -204,15 +369,30 @@ int init_test_probes(void) errors++; num_tests++; + ret = test_kprobes(); + if (ret < 0) + errors++; + + num_tests++; ret = test_jprobe(); if (ret < 0) errors++; + num_tests++; + ret = test_jprobes(); + if (ret < 0) + errors++; + #ifdef CONFIG_KRETPROBES num_tests++; ret = test_kretprobe(); if (ret < 0) errors++; + + num_tests++; + ret = test_kretprobes(); + if (ret < 0) + errors++; #endif /* CONFIG_KRETPROBES */ if (errors) diff --git a/kernel/time.c b/kernel/time.c index d63a433..4886e3c 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -37,6 +37,7 @@ #include <linux/fs.h> #include <linux/slab.h> #include <linux/math64.h> +#include <linux/ptrace.h> #include <asm/uaccess.h> #include <asm/unistd.h> @@ -65,8 +66,9 @@ asmlinkage long sys_time(time_t __user * tloc) if (tloc) { if (put_user(i,tloc)) - i = -EFAULT; + return -EFAULT; } + force_successful_syscall_return(); return i; } diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index f8d9680..ea2f48a 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -166,6 +166,8 @@ static void clockevents_notify_released(void) void clockevents_register_device(struct clock_event_device *dev) { BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); + BUG_ON(!dev->cpumask); + /* * A nsec2cyc multiplicator of 0 is invalid and we'd crash * on it, so fix it up and emit a warning: diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 9ed2eec..ca89e15 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -145,10 +145,11 @@ static void clocksource_watchdog(unsigned long data) * Cycle through CPUs to check if the CPUs stay * synchronized to each other. */ - int next_cpu = next_cpu_nr(raw_smp_processor_id(), cpu_online_map); + int next_cpu = cpumask_next(raw_smp_processor_id(), + cpu_online_mask); if (next_cpu >= nr_cpu_ids) - next_cpu = first_cpu(cpu_online_map); + next_cpu = cpumask_first(cpu_online_mask); watchdog_timer.expires += WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, next_cpu); } @@ -173,7 +174,7 @@ static void clocksource_check_watchdog(struct clocksource *cs) watchdog_last = watchdog->read(); watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, - first_cpu(cpu_online_map)); + cpumask_first(cpu_online_mask)); } } else { if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) @@ -195,7 +196,7 @@ static void clocksource_check_watchdog(struct clocksource *cs) watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; add_timer_on(&watchdog_timer, - first_cpu(cpu_online_map)); + cpumask_first(cpu_online_mask)); } } } diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 1ca9955..06f1975 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -45,7 +45,7 @@ * * The value 8 is somewhat carefully chosen, as anything * larger can result in overflows. NSEC_PER_JIFFY grows as - * HZ shrinks, so values greater then 8 overflow 32bits when + * HZ shrinks, so values greater than 8 overflow 32bits when * HZ=100. */ #define JIFFIES_SHIFT 8 diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 8ff15e5..f5f793d 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -131,7 +131,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) { enum hrtimer_restart res = HRTIMER_NORESTART; - write_seqlock_irq(&xtime_lock); + write_seqlock(&xtime_lock); switch (time_state) { case TIME_OK: @@ -164,7 +164,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) } update_vsyscall(&xtime, clock); - write_sequnlock_irq(&xtime_lock); + write_sequnlock(&xtime_lock); return res; } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index f98a1b7..118a3b3 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -28,7 +28,9 @@ */ struct tick_device tick_broadcast_device; -static cpumask_t tick_broadcast_mask; +/* FIXME: Use cpumask_var_t. */ +static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS); +static DECLARE_BITMAP(tmpmask, NR_CPUS); static DEFINE_SPINLOCK(tick_broadcast_lock); static int tick_broadcast_force; @@ -46,9 +48,9 @@ struct tick_device *tick_get_broadcast_device(void) return &tick_broadcast_device; } -cpumask_t *tick_get_broadcast_mask(void) +struct cpumask *tick_get_broadcast_mask(void) { - return &tick_broadcast_mask; + return to_cpumask(tick_broadcast_mask); } /* @@ -72,7 +74,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev) clockevents_exchange_device(NULL, dev); tick_broadcast_device.evtdev = dev; - if (!cpus_empty(tick_broadcast_mask)) + if (!cpumask_empty(tick_get_broadcast_mask())) tick_broadcast_start_periodic(dev); return 1; } @@ -104,7 +106,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) */ if (!tick_device_is_functional(dev)) { dev->event_handler = tick_handle_periodic; - cpu_set(cpu, tick_broadcast_mask); + cpumask_set_cpu(cpu, tick_get_broadcast_mask()); tick_broadcast_start_periodic(tick_broadcast_device.evtdev); ret = 1; } else { @@ -116,7 +118,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) { int cpu = smp_processor_id(); - cpu_clear(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_get_broadcast_mask()); tick_broadcast_clear_oneshot(cpu); } } @@ -125,9 +127,9 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) } /* - * Broadcast the event to the cpus, which are set in the mask + * Broadcast the event to the cpus, which are set in the mask (mangled). */ -static void tick_do_broadcast(cpumask_t mask) +static void tick_do_broadcast(struct cpumask *mask) { int cpu = smp_processor_id(); struct tick_device *td; @@ -135,21 +137,20 @@ static void tick_do_broadcast(cpumask_t mask) /* * Check, if the current cpu is in the mask */ - if (cpu_isset(cpu, mask)) { - cpu_clear(cpu, mask); + if (cpumask_test_cpu(cpu, mask)) { + cpumask_clear_cpu(cpu, mask); td = &per_cpu(tick_cpu_device, cpu); td->evtdev->event_handler(td->evtdev); } - if (!cpus_empty(mask)) { + if (!cpumask_empty(mask)) { /* * It might be necessary to actually check whether the devices * have different broadcast functions. For now, just use the * one of the first device. This works as long as we have this * misfeature only on x86 (lapic) */ - cpu = first_cpu(mask); - td = &per_cpu(tick_cpu_device, cpu); + td = &per_cpu(tick_cpu_device, cpumask_first(mask)); td->evtdev->broadcast(mask); } } @@ -160,12 +161,11 @@ static void tick_do_broadcast(cpumask_t mask) */ static void tick_do_periodic_broadcast(void) { - cpumask_t mask; - spin_lock(&tick_broadcast_lock); - cpus_and(mask, cpu_online_map, tick_broadcast_mask); - tick_do_broadcast(mask); + cpumask_and(to_cpumask(tmpmask), + cpu_online_mask, tick_get_broadcast_mask()); + tick_do_broadcast(to_cpumask(tmpmask)); spin_unlock(&tick_broadcast_lock); } @@ -228,13 +228,13 @@ static void tick_do_broadcast_on_off(void *why) if (!tick_device_is_functional(dev)) goto out; - bc_stopped = cpus_empty(tick_broadcast_mask); + bc_stopped = cpumask_empty(tick_get_broadcast_mask()); switch (*reason) { case CLOCK_EVT_NOTIFY_BROADCAST_ON: case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: - if (!cpu_isset(cpu, tick_broadcast_mask)) { - cpu_set(cpu, tick_broadcast_mask); + if (!cpumask_test_cpu(cpu, tick_get_broadcast_mask())) { + cpumask_set_cpu(cpu, tick_get_broadcast_mask()); if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) clockevents_shutdown(dev); @@ -244,8 +244,8 @@ static void tick_do_broadcast_on_off(void *why) break; case CLOCK_EVT_NOTIFY_BROADCAST_OFF: if (!tick_broadcast_force && - cpu_isset(cpu, tick_broadcast_mask)) { - cpu_clear(cpu, tick_broadcast_mask); + cpumask_test_cpu(cpu, tick_get_broadcast_mask())) { + cpumask_clear_cpu(cpu, tick_get_broadcast_mask()); if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(dev, 0); @@ -253,7 +253,7 @@ static void tick_do_broadcast_on_off(void *why) break; } - if (cpus_empty(tick_broadcast_mask)) { + if (cpumask_empty(tick_get_broadcast_mask())) { if (!bc_stopped) clockevents_shutdown(bc); } else if (bc_stopped) { @@ -272,7 +272,7 @@ out: */ void tick_broadcast_on_off(unsigned long reason, int *oncpu) { - if (!cpu_isset(*oncpu, cpu_online_map)) + if (!cpumask_test_cpu(*oncpu, cpu_online_mask)) printk(KERN_ERR "tick-broadcast: ignoring broadcast for " "offline CPU #%d\n", *oncpu); else @@ -303,10 +303,10 @@ void tick_shutdown_broadcast(unsigned int *cpup) spin_lock_irqsave(&tick_broadcast_lock, flags); bc = tick_broadcast_device.evtdev; - cpu_clear(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_get_broadcast_mask()); if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { - if (bc && cpus_empty(tick_broadcast_mask)) + if (bc && cpumask_empty(tick_get_broadcast_mask())) clockevents_shutdown(bc); } @@ -342,10 +342,10 @@ int tick_resume_broadcast(void) switch (tick_broadcast_device.mode) { case TICKDEV_MODE_PERIODIC: - if(!cpus_empty(tick_broadcast_mask)) + if (!cpumask_empty(tick_get_broadcast_mask())) tick_broadcast_start_periodic(bc); - broadcast = cpu_isset(smp_processor_id(), - tick_broadcast_mask); + broadcast = cpumask_test_cpu(smp_processor_id(), + tick_get_broadcast_mask()); break; case TICKDEV_MODE_ONESHOT: broadcast = tick_resume_broadcast_oneshot(bc); @@ -360,14 +360,15 @@ int tick_resume_broadcast(void) #ifdef CONFIG_TICK_ONESHOT -static cpumask_t tick_broadcast_oneshot_mask; +/* FIXME: use cpumask_var_t. */ +static DECLARE_BITMAP(tick_broadcast_oneshot_mask, NR_CPUS); /* - * Debugging: see timer_list.c + * Exposed for debugging: see timer_list.c */ -cpumask_t *tick_get_broadcast_oneshot_mask(void) +struct cpumask *tick_get_broadcast_oneshot_mask(void) { - return &tick_broadcast_oneshot_mask; + return to_cpumask(tick_broadcast_oneshot_mask); } static int tick_broadcast_set_event(ktime_t expires, int force) @@ -389,7 +390,7 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc) */ void tick_check_oneshot_broadcast(int cpu) { - if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) { + if (cpumask_test_cpu(cpu, to_cpumask(tick_broadcast_oneshot_mask))) { struct tick_device *td = &per_cpu(tick_cpu_device, cpu); clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT); @@ -402,7 +403,6 @@ void tick_check_oneshot_broadcast(int cpu) static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) { struct tick_device *td; - cpumask_t mask; ktime_t now, next_event; int cpu; @@ -410,13 +410,13 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) again: dev->next_event.tv64 = KTIME_MAX; next_event.tv64 = KTIME_MAX; - mask = CPU_MASK_NONE; + cpumask_clear(to_cpumask(tmpmask)); now = ktime_get(); /* Find all expired events */ - for_each_cpu_mask_nr(cpu, tick_broadcast_oneshot_mask) { + for_each_cpu(cpu, tick_get_broadcast_oneshot_mask()) { td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev->next_event.tv64 <= now.tv64) - cpu_set(cpu, mask); + cpumask_set_cpu(cpu, to_cpumask(tmpmask)); else if (td->evtdev->next_event.tv64 < next_event.tv64) next_event.tv64 = td->evtdev->next_event.tv64; } @@ -424,7 +424,7 @@ again: /* * Wakeup the cpus which have an expired event. */ - tick_do_broadcast(mask); + tick_do_broadcast(to_cpumask(tmpmask)); /* * Two reasons for reprogram: @@ -476,15 +476,16 @@ void tick_broadcast_oneshot_control(unsigned long reason) goto out; if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { - if (!cpu_isset(cpu, tick_broadcast_oneshot_mask)) { - cpu_set(cpu, tick_broadcast_oneshot_mask); + if (!cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) { + cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask()); clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); if (dev->next_event.tv64 < bc->next_event.tv64) tick_broadcast_set_event(dev->next_event, 1); } } else { - if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) { - cpu_clear(cpu, tick_broadcast_oneshot_mask); + if (cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) { + cpumask_clear_cpu(cpu, + tick_get_broadcast_oneshot_mask()); clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); if (dev->next_event.tv64 != KTIME_MAX) tick_program_event(dev->next_event, 1); @@ -502,15 +503,16 @@ out: */ static void tick_broadcast_clear_oneshot(int cpu) { - cpu_clear(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask()); } -static void tick_broadcast_init_next_event(cpumask_t *mask, ktime_t expires) +static void tick_broadcast_init_next_event(struct cpumask *mask, + ktime_t expires) { struct tick_device *td; int cpu; - for_each_cpu_mask_nr(cpu, *mask) { + for_each_cpu(cpu, mask) { td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev) td->evtdev->next_event = expires; @@ -526,7 +528,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) if (bc->event_handler != tick_handle_oneshot_broadcast) { int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC; int cpu = smp_processor_id(); - cpumask_t mask; bc->event_handler = tick_handle_oneshot_broadcast; clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); @@ -540,13 +541,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) * oneshot_mask bits for those and program the * broadcast device to fire. */ - mask = tick_broadcast_mask; - cpu_clear(cpu, mask); - cpus_or(tick_broadcast_oneshot_mask, - tick_broadcast_oneshot_mask, mask); - - if (was_periodic && !cpus_empty(mask)) { - tick_broadcast_init_next_event(&mask, tick_next_period); + cpumask_copy(to_cpumask(tmpmask), tick_get_broadcast_mask()); + cpumask_clear_cpu(cpu, to_cpumask(tmpmask)); + cpumask_or(tick_get_broadcast_oneshot_mask(), + tick_get_broadcast_oneshot_mask(), + to_cpumask(tmpmask)); + + if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) { + tick_broadcast_init_next_event(to_cpumask(tmpmask), + tick_next_period); tick_broadcast_set_event(tick_next_period, 1); } else bc->next_event.tv64 = KTIME_MAX; @@ -585,7 +588,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) * Clear the broadcast mask flag for the dead cpu, but do not * stop the broadcast device! */ - cpu_clear(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask()); spin_unlock_irqrestore(&tick_broadcast_lock, flags); } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index df12434..63e05d4 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -136,7 +136,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) */ static void tick_setup_device(struct tick_device *td, struct clock_event_device *newdev, int cpu, - const cpumask_t *cpumask) + const struct cpumask *cpumask) { ktime_t next_event; void (*handler)(struct clock_event_device *) = NULL; @@ -171,8 +171,8 @@ static void tick_setup_device(struct tick_device *td, * When the device is not per cpu, pin the interrupt to the * current cpu: */ - if (!cpus_equal(newdev->cpumask, *cpumask)) - irq_set_affinity(newdev->irq, *cpumask); + if (!cpumask_equal(newdev->cpumask, cpumask)) + irq_set_affinity(newdev->irq, cpumask); /* * When global broadcasting is active, check if the current @@ -202,14 +202,14 @@ static int tick_check_new_device(struct clock_event_device *newdev) spin_lock_irqsave(&tick_device_lock, flags); cpu = smp_processor_id(); - if (!cpu_isset(cpu, newdev->cpumask)) + if (!cpumask_test_cpu(cpu, newdev->cpumask)) goto out_bc; td = &per_cpu(tick_cpu_device, cpu); curdev = td->evtdev; /* cpu local device ? */ - if (!cpus_equal(newdev->cpumask, cpumask_of_cpu(cpu))) { + if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) { /* * If the cpu affinity of the device interrupt can not @@ -222,7 +222,7 @@ static int tick_check_new_device(struct clock_event_device *newdev) * If we have a cpu local device already, do not replace it * by a non cpu local device */ - if (curdev && cpus_equal(curdev->cpumask, cpumask_of_cpu(cpu))) + if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu))) goto out_bc; } @@ -254,7 +254,7 @@ static int tick_check_new_device(struct clock_event_device *newdev) curdev = NULL; } clockevents_exchange_device(curdev, newdev); - tick_setup_device(td, newdev, cpu, &cpumask_of_cpu(cpu)); + tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) tick_oneshot_notify(); @@ -299,9 +299,9 @@ static void tick_shutdown(unsigned int *cpup) } /* Transfer the do_timer job away from this cpu */ if (*cpup == tick_do_timer_cpu) { - int cpu = first_cpu(cpu_online_map); + int cpu = cpumask_first(cpu_online_mask); - tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu : + tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu : TICK_DO_TIMER_NONE; } spin_unlock_irqrestore(&tick_device_lock, flags); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 342fc9c..1b6c05b 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -144,7 +144,7 @@ void tick_nohz_update_jiffies(void) if (!ts->tick_stopped) return; - cpu_clear(cpu, nohz_cpu_mask); + cpumask_clear_cpu(cpu, nohz_cpu_mask); now = ktime_get(); ts->idle_waketime = now; @@ -247,7 +247,7 @@ void tick_nohz_stop_sched_tick(int inidle) if (need_resched()) goto end; - if (unlikely(local_softirq_pending())) { + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { static int ratelimit; if (ratelimit < 10) { @@ -282,8 +282,31 @@ void tick_nohz_stop_sched_tick(int inidle) /* Schedule the tick, if we are at least one jiffie off */ if ((long)delta_jiffies >= 1) { + /* + * calculate the expiry time for the next timer wheel + * timer + */ + expires = ktime_add_ns(last_update, tick_period.tv64 * + delta_jiffies); + + /* + * If this cpu is the one which updates jiffies, then + * give up the assignment and let it be taken by the + * cpu which runs the tick timer next, which might be + * this cpu as well. If we don't drop this here the + * jiffies might be stale and do_timer() never + * invoked. + */ + if (cpu == tick_do_timer_cpu) + tick_do_timer_cpu = TICK_DO_TIMER_NONE; + if (delta_jiffies > 1) - cpu_set(cpu, nohz_cpu_mask); + cpumask_set_cpu(cpu, nohz_cpu_mask); + + /* Skip reprogram of event if its not changed */ + if (ts->tick_stopped && ktime_equal(expires, dev->next_event)) + goto out; + /* * nohz_stop_sched_tick can be called several times before * the nohz_restart_sched_tick is called. This happens when @@ -296,7 +319,7 @@ void tick_nohz_stop_sched_tick(int inidle) /* * sched tick not stopped! */ - cpu_clear(cpu, nohz_cpu_mask); + cpumask_clear_cpu(cpu, nohz_cpu_mask); goto out; } @@ -306,17 +329,6 @@ void tick_nohz_stop_sched_tick(int inidle) rcu_enter_nohz(); } - /* - * If this cpu is the one which updates jiffies, then - * give up the assignment and let it be taken by the - * cpu which runs the tick timer next, which might be - * this cpu as well. If we don't drop this here the - * jiffies might be stale and do_timer() never - * invoked. - */ - if (cpu == tick_do_timer_cpu) - tick_do_timer_cpu = TICK_DO_TIMER_NONE; - ts->idle_sleeps++; /* @@ -332,12 +344,7 @@ void tick_nohz_stop_sched_tick(int inidle) goto out; } - /* - * calculate the expiry time for the next timer wheel - * timer - */ - expires = ktime_add_ns(last_update, tick_period.tv64 * - delta_jiffies); + /* Mark expiries */ ts->idle_expires = expires; if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { @@ -354,7 +361,7 @@ void tick_nohz_stop_sched_tick(int inidle) * softirq. */ tick_do_update_jiffies64(ktime_get()); - cpu_clear(cpu, nohz_cpu_mask); + cpumask_clear_cpu(cpu, nohz_cpu_mask); } raise_softirq_irqoff(TIMER_SOFTIRQ); out: @@ -412,7 +419,9 @@ void tick_nohz_restart_sched_tick(void) { int cpu = smp_processor_id(); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); +#ifndef CONFIG_VIRT_CPU_ACCOUNTING unsigned long ticks; +#endif ktime_t now; local_irq_disable(); @@ -432,8 +441,9 @@ void tick_nohz_restart_sched_tick(void) select_nohz_load_balancer(0); now = ktime_get(); tick_do_update_jiffies64(now); - cpu_clear(cpu, nohz_cpu_mask); + cpumask_clear_cpu(cpu, nohz_cpu_mask); +#ifndef CONFIG_VIRT_CPU_ACCOUNTING /* * We stopped the tick in idle. Update process times would miss the * time we slept as update_process_times does only a 1 tick @@ -443,12 +453,9 @@ void tick_nohz_restart_sched_tick(void) /* * We might be one off. Do not randomly account a huge number of ticks! */ - if (ticks && ticks < LONG_MAX) { - add_preempt_count(HARDIRQ_OFFSET); - account_system_time(current, HARDIRQ_OFFSET, - jiffies_to_cputime(ticks)); - sub_preempt_count(HARDIRQ_OFFSET); - } + if (ticks && ticks < LONG_MAX) + account_idle_ticks(ticks); +#endif touch_softlockup_watchdog(); /* @@ -681,7 +688,6 @@ void tick_setup_sched_timer(void) */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ts->sched_timer.function = tick_sched_timer; - ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; /* Get the next period (per cpu) */ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index fa05e88..900f1b6 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -46,6 +46,9 @@ struct timespec xtime __attribute__ ((aligned (16))); struct timespec wall_to_monotonic __attribute__ ((aligned (16))); static unsigned long total_sleep_time; /* seconds */ +/* flag for if timekeeping is suspended */ +int __read_mostly timekeeping_suspended; + static struct timespec xtime_cache __attribute__ ((aligned (16))); void update_xtime_cache(u64 nsec) { @@ -92,6 +95,8 @@ void getnstimeofday(struct timespec *ts) unsigned long seq; s64 nsecs; + WARN_ON(timekeeping_suspended); + do { seq = read_seqbegin(&xtime_lock); @@ -299,8 +304,6 @@ void __init timekeeping_init(void) write_sequnlock_irqrestore(&xtime_lock, flags); } -/* flag for if timekeeping is suspended */ -static int timekeeping_suspended; /* time in seconds when suspend began */ static unsigned long timekeeping_suspend_time; diff --git a/kernel/timer.c b/kernel/timer.c index dbd50fa..dee3f64 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1018,21 +1018,6 @@ unsigned long get_next_timer_interrupt(unsigned long now) } #endif -#ifndef CONFIG_VIRT_CPU_ACCOUNTING -void account_process_tick(struct task_struct *p, int user_tick) -{ - cputime_t one_jiffy = jiffies_to_cputime(1); - - if (user_tick) { - account_user_time(p, one_jiffy); - account_user_time_scaled(p, cputime_to_scaled(one_jiffy)); - } else { - account_system_time(p, HARDIRQ_OFFSET, one_jiffy); - account_system_time_scaled(p, cputime_to_scaled(one_jiffy)); - } -} -#endif - /* * Called from the timer interrupt handler to charge one tick to the current * process. user_tick is 1 if the tick is user time, 0 for system. @@ -1192,25 +1177,25 @@ asmlinkage long sys_getppid(void) asmlinkage long sys_getuid(void) { /* Only we change this so SMP safe */ - return current->uid; + return current_uid(); } asmlinkage long sys_geteuid(void) { /* Only we change this so SMP safe */ - return current->euid; + return current_euid(); } asmlinkage long sys_getgid(void) { /* Only we change this so SMP safe */ - return current->gid; + return current_gid(); } asmlinkage long sys_getegid(void) { /* Only we change this so SMP safe */ - return current->egid; + return current_egid(); } #endif diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 33dbefd..e2a4ff6 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -3,18 +3,34 @@ # select HAVE_FUNCTION_TRACER: # +config USER_STACKTRACE_SUPPORT + bool + config NOP_TRACER bool config HAVE_FUNCTION_TRACER bool +config HAVE_FUNCTION_GRAPH_TRACER + bool + +config HAVE_FUNCTION_TRACE_MCOUNT_TEST + bool + help + This gets selected when the arch tests the function_trace_stop + variable at the mcount call site. Otherwise, this variable + is tested by the called function. + config HAVE_DYNAMIC_FTRACE bool config HAVE_FTRACE_MCOUNT_RECORD bool +config HAVE_HW_BRANCH_TRACER + bool + config TRACER_MAX_TRACE bool @@ -47,6 +63,20 @@ config FUNCTION_TRACER (the bootup default), then the overhead of the instructions is very small and not measurable even in micro-benchmarks. +config FUNCTION_GRAPH_TRACER + bool "Kernel Function Graph Tracer" + depends on HAVE_FUNCTION_GRAPH_TRACER + depends on FUNCTION_TRACER + default y + help + Enable the kernel to trace a function at both its return + and its entry. + It's first purpose is to trace the duration of functions and + draw a call graph for each thread with some informations like + the return value. + This is done by setting the current return address on the current + task structure into a stack of calls. + config IRQSOFF_TRACER bool "Interrupts-off Latency Tracer" default n @@ -138,6 +168,70 @@ config BOOT_TRACER selected, because the self-tests are an initcall as well and that would invalidate the boot trace. ) +config TRACE_BRANCH_PROFILING + bool "Trace likely/unlikely profiler" + depends on DEBUG_KERNEL + select TRACING + help + This tracer profiles all the the likely and unlikely macros + in the kernel. It will display the results in: + + /debugfs/tracing/profile_annotated_branch + + Note: this will add a significant overhead, only turn this + on if you need to profile the system's use of these macros. + + Say N if unsure. + +config PROFILE_ALL_BRANCHES + bool "Profile all if conditionals" + depends on TRACE_BRANCH_PROFILING + help + This tracer profiles all branch conditions. Every if () + taken in the kernel is recorded whether it hit or miss. + The results will be displayed in: + + /debugfs/tracing/profile_branch + + This configuration, when enabled, will impose a great overhead + on the system. This should only be enabled when the system + is to be analyzed + + Say N if unsure. + +config TRACING_BRANCHES + bool + help + Selected by tracers that will trace the likely and unlikely + conditions. This prevents the tracers themselves from being + profiled. Profiling the tracing infrastructure can only happen + when the likelys and unlikelys are not being traced. + +config BRANCH_TRACER + bool "Trace likely/unlikely instances" + depends on TRACE_BRANCH_PROFILING + select TRACING_BRANCHES + help + This traces the events of likely and unlikely condition + calls in the kernel. The difference between this and the + "Trace likely/unlikely profiler" is that this is not a + histogram of the callers, but actually places the calling + events into a running trace buffer to see when and where the + events happened, as well as their results. + + Say N if unsure. + +config POWER_TRACER + bool "Trace power consumption behavior" + depends on DEBUG_KERNEL + depends on X86 + select TRACING + help + This tracer helps developers to analyze and optimize the kernels + power management decisions, specifically the C-state and P-state + behavior. + + config STACK_TRACER bool "Trace max stack" depends on HAVE_FUNCTION_TRACER @@ -150,13 +244,26 @@ config STACK_TRACER This tracer works by hooking into every function call that the kernel executes, and keeping a maximum stack depth value and - stack-trace saved. Because this logic has to execute in every - kernel function, all the time, this option can slow down the - kernel measurably and is generally intended for kernel - developers only. + stack-trace saved. If this is configured with DYNAMIC_FTRACE + then it will not have any overhead while the stack tracer + is disabled. + + To enable the stack tracer on bootup, pass in 'stacktrace' + on the kernel command line. + + The stack tracer can also be enabled or disabled via the + sysctl kernel.stack_tracer_enabled Say N if unsure. +config HW_BRANCH_TRACER + depends on HAVE_HW_BRANCH_TRACER + bool "Trace hw branches" + select TRACING + help + This tracer records all branches on the system in a circular + buffer giving access to the last N branches for each cpu. + config DYNAMIC_FTRACE bool "enable/disable ftrace tracepoints dynamically" depends on FUNCTION_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index c8228b1..349d5a9 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -10,6 +10,11 @@ CFLAGS_trace_selftest_dynamic.o = -pg obj-y += trace_selftest_dynamic.o endif +# If unlikely tracing is enabled, do not trace these files +ifdef CONFIG_TRACING_BRANCHES +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING +endif + obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o obj-$(CONFIG_RING_BUFFER) += ring_buffer.o @@ -24,5 +29,9 @@ obj-$(CONFIG_NOP_TRACER) += trace_nop.o obj-$(CONFIG_STACK_TRACER) += trace_stack.o obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o obj-$(CONFIG_BOOT_TRACER) += trace_boot.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o +obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o +obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o +obj-$(CONFIG_POWER_TRACER) += trace_power.o libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 78db083..2f32969 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -47,6 +47,13 @@ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; +/* set when tracing only a pid */ +struct pid *ftrace_pid_trace; +static struct pid * const ftrace_swapper_pid = &init_struct_pid; + +/* Quick disabling of function tracer. */ +int function_trace_stop; + /* * ftrace_disabled is set when an anomaly is discovered. * ftrace_disabled is much stronger than ftrace_enabled. @@ -55,6 +62,7 @@ static int ftrace_disabled __read_mostly; static DEFINE_SPINLOCK(ftrace_lock); static DEFINE_MUTEX(ftrace_sysctl_lock); +static DEFINE_MUTEX(ftrace_start_lock); static struct ftrace_ops ftrace_list_end __read_mostly = { @@ -63,6 +71,8 @@ static struct ftrace_ops ftrace_list_end __read_mostly = static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; +ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; +ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) { @@ -79,6 +89,21 @@ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) }; } +static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip) +{ + if (!test_tsk_trace_trace(current)) + return; + + ftrace_pid_function(ip, parent_ip); +} + +static void set_ftrace_pid_function(ftrace_func_t func) +{ + /* do not set ftrace_pid_function to itself! */ + if (func != ftrace_pid_func) + ftrace_pid_function = func; +} + /** * clear_ftrace_function - reset the ftrace function * @@ -88,7 +113,23 @@ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) void clear_ftrace_function(void) { ftrace_trace_function = ftrace_stub; + __ftrace_trace_function = ftrace_stub; + ftrace_pid_function = ftrace_stub; +} + +#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST +/* + * For those archs that do not test ftrace_trace_stop in their + * mcount call site, we need to do it from C. + */ +static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) +{ + if (function_trace_stop) + return; + + __ftrace_trace_function(ip, parent_ip); } +#endif static int __register_ftrace_function(struct ftrace_ops *ops) { @@ -106,14 +147,28 @@ static int __register_ftrace_function(struct ftrace_ops *ops) ftrace_list = ops; if (ftrace_enabled) { + ftrace_func_t func; + + if (ops->next == &ftrace_list_end) + func = ops->func; + else + func = ftrace_list_func; + + if (ftrace_pid_trace) { + set_ftrace_pid_function(func); + func = ftrace_pid_func; + } + /* * For one func, simply call it directly. * For more than one func, call the chain. */ - if (ops->next == &ftrace_list_end) - ftrace_trace_function = ops->func; - else - ftrace_trace_function = ftrace_list_func; +#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST + ftrace_trace_function = func; +#else + __ftrace_trace_function = func; + ftrace_trace_function = ftrace_test_stop_func; +#endif } spin_unlock(&ftrace_lock); @@ -152,9 +207,19 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) if (ftrace_enabled) { /* If we only have one func left, then call that directly */ - if (ftrace_list == &ftrace_list_end || - ftrace_list->next == &ftrace_list_end) - ftrace_trace_function = ftrace_list->func; + if (ftrace_list->next == &ftrace_list_end) { + ftrace_func_t func = ftrace_list->func; + + if (ftrace_pid_trace) { + set_ftrace_pid_function(func); + func = ftrace_pid_func; + } +#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST + ftrace_trace_function = func; +#else + __ftrace_trace_function = func; +#endif + } } out: @@ -163,6 +228,36 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) return ret; } +static void ftrace_update_pid_func(void) +{ + ftrace_func_t func; + + /* should not be called from interrupt context */ + spin_lock(&ftrace_lock); + + if (ftrace_trace_function == ftrace_stub) + goto out; + + func = ftrace_trace_function; + + if (ftrace_pid_trace) { + set_ftrace_pid_function(func); + func = ftrace_pid_func; + } else { + if (func == ftrace_pid_func) + func = ftrace_pid_function; + } + +#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST + ftrace_trace_function = func; +#else + __ftrace_trace_function = func; +#endif + + out: + spin_unlock(&ftrace_lock); +} + #ifdef CONFIG_DYNAMIC_FTRACE #ifndef CONFIG_FTRACE_MCOUNT_RECORD # error Dynamic ftrace depends on MCOUNT_RECORD @@ -182,6 +277,8 @@ enum { FTRACE_UPDATE_TRACE_FUNC = (1 << 2), FTRACE_ENABLE_MCOUNT = (1 << 3), FTRACE_DISABLE_MCOUNT = (1 << 4), + FTRACE_START_FUNC_RET = (1 << 5), + FTRACE_STOP_FUNC_RET = (1 << 6), }; static int ftrace_filtered; @@ -308,7 +405,7 @@ ftrace_record_ip(unsigned long ip) { struct dyn_ftrace *rec; - if (!ftrace_enabled || ftrace_disabled) + if (ftrace_disabled) return NULL; rec = ftrace_alloc_dyn_node(ip); @@ -322,14 +419,51 @@ ftrace_record_ip(unsigned long ip) return rec; } -#define FTRACE_ADDR ((long)(ftrace_caller)) +static void print_ip_ins(const char *fmt, unsigned char *p) +{ + int i; + + printk(KERN_CONT "%s", fmt); + + for (i = 0; i < MCOUNT_INSN_SIZE; i++) + printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); +} + +static void ftrace_bug(int failed, unsigned long ip) +{ + switch (failed) { + case -EFAULT: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on modifying "); + print_ip_sym(ip); + break; + case -EINVAL: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace failed to modify "); + print_ip_sym(ip); + print_ip_ins(" actual: ", (unsigned char *)ip); + printk(KERN_CONT "\n"); + break; + case -EPERM: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on writing "); + print_ip_sym(ip); + break; + default: + FTRACE_WARN_ON_ONCE(1); + pr_info("ftrace faulted on unknown error "); + print_ip_sym(ip); + } +} + static int -__ftrace_replace_code(struct dyn_ftrace *rec, - unsigned char *nop, int enable) +__ftrace_replace_code(struct dyn_ftrace *rec, int enable) { unsigned long ip, fl; - unsigned char *call, *old, *new; + unsigned long ftrace_addr; + + ftrace_addr = (unsigned long)ftrace_caller; ip = rec->ip; @@ -388,34 +522,28 @@ __ftrace_replace_code(struct dyn_ftrace *rec, } } - call = ftrace_call_replace(ip, FTRACE_ADDR); - - if (rec->flags & FTRACE_FL_ENABLED) { - old = nop; - new = call; - } else { - old = call; - new = nop; - } - - return ftrace_modify_code(ip, old, new); + if (rec->flags & FTRACE_FL_ENABLED) + return ftrace_make_call(rec, ftrace_addr); + else + return ftrace_make_nop(NULL, rec, ftrace_addr); } static void ftrace_replace_code(int enable) { int i, failed; - unsigned char *nop = NULL; struct dyn_ftrace *rec; struct ftrace_page *pg; - nop = ftrace_nop_replace(); - for (pg = ftrace_pages_start; pg; pg = pg->next) { for (i = 0; i < pg->index; i++) { rec = &pg->records[i]; - /* don't modify code that has already faulted */ - if (rec->flags & FTRACE_FL_FAILED) + /* + * Skip over free records and records that have + * failed. + */ + if (rec->flags & FTRACE_FL_FREE || + rec->flags & FTRACE_FL_FAILED) continue; /* ignore updates to this record's mcount site */ @@ -426,68 +554,30 @@ static void ftrace_replace_code(int enable) unfreeze_record(rec); } - failed = __ftrace_replace_code(rec, nop, enable); + failed = __ftrace_replace_code(rec, enable); if (failed && (rec->flags & FTRACE_FL_CONVERTED)) { rec->flags |= FTRACE_FL_FAILED; if ((system_state == SYSTEM_BOOTING) || !core_kernel_text(rec->ip)) { ftrace_free_rec(rec); - } + } else + ftrace_bug(failed, rec->ip); } } } } -static void print_ip_ins(const char *fmt, unsigned char *p) -{ - int i; - - printk(KERN_CONT "%s", fmt); - - for (i = 0; i < MCOUNT_INSN_SIZE; i++) - printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); -} - static int -ftrace_code_disable(struct dyn_ftrace *rec) +ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) { unsigned long ip; - unsigned char *nop, *call; int ret; ip = rec->ip; - nop = ftrace_nop_replace(); - call = ftrace_call_replace(ip, mcount_addr); - - ret = ftrace_modify_code(ip, call, nop); + ret = ftrace_make_nop(mod, rec, mcount_addr); if (ret) { - switch (ret) { - case -EFAULT: - FTRACE_WARN_ON_ONCE(1); - pr_info("ftrace faulted on modifying "); - print_ip_sym(ip); - break; - case -EINVAL: - FTRACE_WARN_ON_ONCE(1); - pr_info("ftrace failed to modify "); - print_ip_sym(ip); - print_ip_ins(" expected: ", call); - print_ip_ins(" actual: ", (unsigned char *)ip); - print_ip_ins(" replace: ", nop); - printk(KERN_CONT "\n"); - break; - case -EPERM: - FTRACE_WARN_ON_ONCE(1); - pr_info("ftrace faulted on writing "); - print_ip_sym(ip); - break; - default: - FTRACE_WARN_ON_ONCE(1); - pr_info("ftrace faulted on unknown error "); - print_ip_sym(ip); - } - + ftrace_bug(ret, ip); rec->flags |= FTRACE_FL_FAILED; return 0; } @@ -506,6 +596,11 @@ static int __ftrace_modify_code(void *data) if (*command & FTRACE_UPDATE_TRACE_FUNC) ftrace_update_ftrace_func(ftrace_trace_function); + if (*command & FTRACE_START_FUNC_RET) + ftrace_enable_ftrace_graph_caller(); + else if (*command & FTRACE_STOP_FUNC_RET) + ftrace_disable_ftrace_graph_caller(); + return 0; } @@ -515,43 +610,43 @@ static void ftrace_run_update_code(int command) } static ftrace_func_t saved_ftrace_func; -static int ftrace_start; -static DEFINE_MUTEX(ftrace_start_lock); +static int ftrace_start_up; -static void ftrace_startup(void) +static void ftrace_startup_enable(int command) { - int command = 0; - - if (unlikely(ftrace_disabled)) - return; - - mutex_lock(&ftrace_start_lock); - ftrace_start++; - command |= FTRACE_ENABLE_CALLS; - if (saved_ftrace_func != ftrace_trace_function) { saved_ftrace_func = ftrace_trace_function; command |= FTRACE_UPDATE_TRACE_FUNC; } if (!command || !ftrace_enabled) - goto out; + return; ftrace_run_update_code(command); - out: - mutex_unlock(&ftrace_start_lock); } -static void ftrace_shutdown(void) +static void ftrace_startup(int command) { - int command = 0; + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftrace_start_lock); + ftrace_start_up++; + command |= FTRACE_ENABLE_CALLS; + ftrace_startup_enable(command); + + mutex_unlock(&ftrace_start_lock); +} + +static void ftrace_shutdown(int command) +{ if (unlikely(ftrace_disabled)) return; mutex_lock(&ftrace_start_lock); - ftrace_start--; - if (!ftrace_start) + ftrace_start_up--; + if (!ftrace_start_up) command |= FTRACE_DISABLE_CALLS; if (saved_ftrace_func != ftrace_trace_function) { @@ -577,8 +672,8 @@ static void ftrace_startup_sysctl(void) mutex_lock(&ftrace_start_lock); /* Force update next time */ saved_ftrace_func = NULL; - /* ftrace_start is true if we want ftrace running */ - if (ftrace_start) + /* ftrace_start_up is true if we want ftrace running */ + if (ftrace_start_up) command |= FTRACE_ENABLE_CALLS; ftrace_run_update_code(command); @@ -593,8 +688,8 @@ static void ftrace_shutdown_sysctl(void) return; mutex_lock(&ftrace_start_lock); - /* ftrace_start is true if ftrace is running */ - if (ftrace_start) + /* ftrace_start_up is true if ftrace is running */ + if (ftrace_start_up) command |= FTRACE_DISABLE_CALLS; ftrace_run_update_code(command); @@ -605,7 +700,7 @@ static cycle_t ftrace_update_time; static unsigned long ftrace_update_cnt; unsigned long ftrace_update_tot_cnt; -static int ftrace_update_code(void) +static int ftrace_update_code(struct module *mod) { struct dyn_ftrace *p, *t; cycle_t start, stop; @@ -622,7 +717,7 @@ static int ftrace_update_code(void) list_del_init(&p->list); /* convert record (i.e, patch mcount-call with NOP) */ - if (ftrace_code_disable(p)) { + if (ftrace_code_disable(mod, p)) { p->flags |= FTRACE_FL_CONVERTED; ftrace_update_cnt++; } else @@ -690,7 +785,6 @@ enum { #define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ struct ftrace_iterator { - loff_t pos; struct ftrace_page *pg; unsigned idx; unsigned flags; @@ -715,6 +809,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) iter->pg = iter->pg->next; iter->idx = 0; goto retry; + } else { + iter->idx = -1; } } else { rec = &iter->pg->records[iter->idx++]; @@ -737,8 +833,6 @@ t_next(struct seq_file *m, void *v, loff_t *pos) } spin_unlock(&ftrace_lock); - iter->pos = *pos; - return rec; } @@ -746,13 +840,15 @@ static void *t_start(struct seq_file *m, loff_t *pos) { struct ftrace_iterator *iter = m->private; void *p = NULL; - loff_t l = -1; - if (*pos > iter->pos) - *pos = iter->pos; + if (*pos > 0) { + if (iter->idx < 0) + return p; + (*pos)--; + iter->idx--; + } - l = *pos; - p = t_next(m, p, &l); + p = t_next(m, p, pos); return p; } @@ -763,21 +859,15 @@ static void t_stop(struct seq_file *m, void *p) static int t_show(struct seq_file *m, void *v) { - struct ftrace_iterator *iter = m->private; struct dyn_ftrace *rec = v; char str[KSYM_SYMBOL_LEN]; - int ret = 0; if (!rec) return 0; kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); - ret = seq_printf(m, "%s\n", str); - if (ret < 0) { - iter->pos--; - iter->idx--; - } + seq_printf(m, "%s\n", str); return 0; } @@ -803,7 +893,6 @@ ftrace_avail_open(struct inode *inode, struct file *file) return -ENOMEM; iter->pg = ftrace_pages_start; - iter->pos = 0; ret = seq_open(file, &show_ftrace_seq_ops); if (!ret) { @@ -890,7 +979,6 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; - iter->pos = 0; iter->flags = enable ? FTRACE_ITER_FILTER : FTRACE_ITER_NOTRACE; @@ -959,6 +1047,13 @@ ftrace_match(unsigned char *buff, int len, int enable) int type = MATCH_FULL; unsigned long flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; unsigned i, match = 0, search_len = 0; + int not = 0; + + if (buff[0] == '!') { + not = 1; + buff++; + len--; + } for (i = 0; i < len; i++) { if (buff[i] == '*') { @@ -1012,8 +1107,12 @@ ftrace_match(unsigned char *buff, int len, int enable) matched = 1; break; } - if (matched) - rec->flags |= flag; + if (matched) { + if (not) + rec->flags &= ~flag; + else + rec->flags |= flag; + } } pg = pg->next; } @@ -1181,7 +1280,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable) mutex_lock(&ftrace_sysctl_lock); mutex_lock(&ftrace_start_lock); - if (ftrace_start && ftrace_enabled) + if (ftrace_start_up && ftrace_enabled) ftrace_run_update_code(FTRACE_ENABLE_CALLS); mutex_unlock(&ftrace_start_lock); mutex_unlock(&ftrace_sysctl_lock); @@ -1233,12 +1332,233 @@ static struct file_operations ftrace_notrace_fops = { .release = ftrace_notrace_release, }; -static __init int ftrace_init_debugfs(void) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +static DEFINE_MUTEX(graph_lock); + +int ftrace_graph_count; +unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly; + +static void * +g_next(struct seq_file *m, void *v, loff_t *pos) { - struct dentry *d_tracer; - struct dentry *entry; + unsigned long *array = m->private; + int index = *pos; - d_tracer = tracing_init_dentry(); + (*pos)++; + + if (index >= ftrace_graph_count) + return NULL; + + return &array[index]; +} + +static void *g_start(struct seq_file *m, loff_t *pos) +{ + void *p = NULL; + + mutex_lock(&graph_lock); + + p = g_next(m, p, pos); + + return p; +} + +static void g_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&graph_lock); +} + +static int g_show(struct seq_file *m, void *v) +{ + unsigned long *ptr = v; + char str[KSYM_SYMBOL_LEN]; + + if (!ptr) + return 0; + + kallsyms_lookup(*ptr, NULL, NULL, NULL, str); + + seq_printf(m, "%s\n", str); + + return 0; +} + +static struct seq_operations ftrace_graph_seq_ops = { + .start = g_start, + .next = g_next, + .stop = g_stop, + .show = g_show, +}; + +static int +ftrace_graph_open(struct inode *inode, struct file *file) +{ + int ret = 0; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + mutex_lock(&graph_lock); + if ((file->f_mode & FMODE_WRITE) && + !(file->f_flags & O_APPEND)) { + ftrace_graph_count = 0; + memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs)); + } + + if (file->f_mode & FMODE_READ) { + ret = seq_open(file, &ftrace_graph_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = ftrace_graph_funcs; + } + } else + file->private_data = ftrace_graph_funcs; + mutex_unlock(&graph_lock); + + return ret; +} + +static ssize_t +ftrace_graph_read(struct file *file, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + if (file->f_mode & FMODE_READ) + return seq_read(file, ubuf, cnt, ppos); + else + return -EPERM; +} + +static int +ftrace_set_func(unsigned long *array, int idx, char *buffer) +{ + char str[KSYM_SYMBOL_LEN]; + struct dyn_ftrace *rec; + struct ftrace_page *pg; + int found = 0; + int i, j; + + if (ftrace_disabled) + return -ENODEV; + + /* should not be called from interrupt context */ + spin_lock(&ftrace_lock); + + for (pg = ftrace_pages_start; pg; pg = pg->next) { + for (i = 0; i < pg->index; i++) { + rec = &pg->records[i]; + + if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE)) + continue; + + kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); + if (strcmp(str, buffer) == 0) { + found = 1; + for (j = 0; j < idx; j++) + if (array[j] == rec->ip) { + found = 0; + break; + } + if (found) + array[idx] = rec->ip; + break; + } + } + } + spin_unlock(&ftrace_lock); + + return found ? 0 : -EINVAL; +} + +static ssize_t +ftrace_graph_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned char buffer[FTRACE_BUFF_MAX+1]; + unsigned long *array; + size_t read = 0; + ssize_t ret; + int index = 0; + char ch; + + if (!cnt || cnt < 0) + return 0; + + mutex_lock(&graph_lock); + + if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) { + ret = -EBUSY; + goto out; + } + + if (file->f_mode & FMODE_READ) { + struct seq_file *m = file->private_data; + array = m->private; + } else + array = file->private_data; + + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + + /* skip white space */ + while (cnt && isspace(ch)) { + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + if (isspace(ch)) { + *ppos += read; + ret = read; + goto out; + } + + while (cnt && !isspace(ch)) { + if (index < FTRACE_BUFF_MAX) + buffer[index++] = ch; + else { + ret = -EINVAL; + goto out; + } + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + buffer[index] = 0; + + /* we allow only one at a time */ + ret = ftrace_set_func(array, ftrace_graph_count, buffer); + if (ret) + goto out; + + ftrace_graph_count++; + + file->f_pos += read; + + ret = read; + out: + mutex_unlock(&graph_lock); + + return ret; +} + +static const struct file_operations ftrace_graph_fops = { + .open = ftrace_graph_open, + .read = ftrace_graph_read, + .write = ftrace_graph_write, +}; +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) +{ + struct dentry *entry; entry = debugfs_create_file("available_filter_functions", 0444, d_tracer, NULL, &ftrace_avail_fops); @@ -1263,12 +1583,20 @@ static __init int ftrace_init_debugfs(void) pr_warning("Could not create debugfs " "'set_ftrace_notrace' entry\n"); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + entry = debugfs_create_file("set_graph_function", 0444, d_tracer, + NULL, + &ftrace_graph_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'set_graph_function' entry\n"); +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + return 0; } -fs_initcall(ftrace_init_debugfs); - -static int ftrace_convert_nops(unsigned long *start, +static int ftrace_convert_nops(struct module *mod, + unsigned long *start, unsigned long *end) { unsigned long *p; @@ -1279,23 +1607,32 @@ static int ftrace_convert_nops(unsigned long *start, p = start; while (p < end) { addr = ftrace_call_adjust(*p++); + /* + * Some architecture linkers will pad between + * the different mcount_loc sections of different + * object files to satisfy alignments. + * Skip any NULL pointers. + */ + if (!addr) + continue; ftrace_record_ip(addr); } /* disable interrupts to prevent kstop machine */ local_irq_save(flags); - ftrace_update_code(); + ftrace_update_code(mod); local_irq_restore(flags); mutex_unlock(&ftrace_start_lock); return 0; } -void ftrace_init_module(unsigned long *start, unsigned long *end) +void ftrace_init_module(struct module *mod, + unsigned long *start, unsigned long *end) { if (ftrace_disabled || start == end) return; - ftrace_convert_nops(start, end); + ftrace_convert_nops(mod, start, end); } extern unsigned long __start_mcount_loc[]; @@ -1325,7 +1662,8 @@ void __init ftrace_init(void) last_ftrace_enabled = ftrace_enabled = 1; - ret = ftrace_convert_nops(__start_mcount_loc, + ret = ftrace_convert_nops(NULL, + __start_mcount_loc, __stop_mcount_loc); return; @@ -1342,12 +1680,186 @@ static int __init ftrace_nodyn_init(void) } device_initcall(ftrace_nodyn_init); -# define ftrace_startup() do { } while (0) -# define ftrace_shutdown() do { } while (0) +static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } +static inline void ftrace_startup_enable(int command) { } +/* Keep as macros so we do not need to define the commands */ +# define ftrace_startup(command) do { } while (0) +# define ftrace_shutdown(command) do { } while (0) # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) #endif /* CONFIG_DYNAMIC_FTRACE */ +static ssize_t +ftrace_pid_read(struct file *file, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + int r; + + if (ftrace_pid_trace == ftrace_swapper_pid) + r = sprintf(buf, "swapper tasks\n"); + else if (ftrace_pid_trace) + r = sprintf(buf, "%u\n", pid_nr(ftrace_pid_trace)); + else + r = sprintf(buf, "no pid\n"); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static void clear_ftrace_swapper(void) +{ + struct task_struct *p; + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) { + p = idle_task(cpu); + clear_tsk_trace_trace(p); + } + put_online_cpus(); +} + +static void set_ftrace_swapper(void) +{ + struct task_struct *p; + int cpu; + + get_online_cpus(); + for_each_online_cpu(cpu) { + p = idle_task(cpu); + set_tsk_trace_trace(p); + } + put_online_cpus(); +} + +static void clear_ftrace_pid(struct pid *pid) +{ + struct task_struct *p; + + do_each_pid_task(pid, PIDTYPE_PID, p) { + clear_tsk_trace_trace(p); + } while_each_pid_task(pid, PIDTYPE_PID, p); + put_pid(pid); +} + +static void set_ftrace_pid(struct pid *pid) +{ + struct task_struct *p; + + do_each_pid_task(pid, PIDTYPE_PID, p) { + set_tsk_trace_trace(p); + } while_each_pid_task(pid, PIDTYPE_PID, p); +} + +static void clear_ftrace_pid_task(struct pid **pid) +{ + if (*pid == ftrace_swapper_pid) + clear_ftrace_swapper(); + else + clear_ftrace_pid(*pid); + + *pid = NULL; +} + +static void set_ftrace_pid_task(struct pid *pid) +{ + if (pid == ftrace_swapper_pid) + set_ftrace_swapper(); + else + set_ftrace_pid(pid); +} + +static ssize_t +ftrace_pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct pid *pid; + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtol(buf, 10, &val); + if (ret < 0) + return ret; + + mutex_lock(&ftrace_start_lock); + if (val < 0) { + /* disable pid tracing */ + if (!ftrace_pid_trace) + goto out; + + clear_ftrace_pid_task(&ftrace_pid_trace); + + } else { + /* swapper task is special */ + if (!val) { + pid = ftrace_swapper_pid; + if (pid == ftrace_pid_trace) + goto out; + } else { + pid = find_get_pid(val); + + if (pid == ftrace_pid_trace) { + put_pid(pid); + goto out; + } + } + + if (ftrace_pid_trace) + clear_ftrace_pid_task(&ftrace_pid_trace); + + if (!pid) + goto out; + + ftrace_pid_trace = pid; + + set_ftrace_pid_task(ftrace_pid_trace); + } + + /* update the function call */ + ftrace_update_pid_func(); + ftrace_startup_enable(0); + + out: + mutex_unlock(&ftrace_start_lock); + + return cnt; +} + +static struct file_operations ftrace_pid_fops = { + .read = ftrace_pid_read, + .write = ftrace_pid_write, +}; + +static __init int ftrace_init_debugfs(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; + + ftrace_init_dyn_debugfs(d_tracer); + + entry = debugfs_create_file("set_ftrace_pid", 0644, d_tracer, + NULL, &ftrace_pid_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'set_ftrace_pid' entry\n"); + return 0; +} + +fs_initcall(ftrace_init_debugfs); + /** * ftrace_kill - kill ftrace * @@ -1381,10 +1893,11 @@ int register_ftrace_function(struct ftrace_ops *ops) return -1; mutex_lock(&ftrace_sysctl_lock); + ret = __register_ftrace_function(ops); - ftrace_startup(); - mutex_unlock(&ftrace_sysctl_lock); + ftrace_startup(0); + mutex_unlock(&ftrace_sysctl_lock); return ret; } @@ -1400,7 +1913,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_sysctl_lock); ret = __unregister_ftrace_function(ops); - ftrace_shutdown(); + ftrace_shutdown(0); mutex_unlock(&ftrace_sysctl_lock); return ret; @@ -1449,3 +1962,153 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, return ret; } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + +static atomic_t ftrace_graph_active; + +int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace) +{ + return 0; +} + +/* The callbacks that hook a function */ +trace_func_graph_ret_t ftrace_graph_return = + (trace_func_graph_ret_t)ftrace_stub; +trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub; + +/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */ +static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) +{ + int i; + int ret = 0; + unsigned long flags; + int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE; + struct task_struct *g, *t; + + for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) { + ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!ret_stack_list[i]) { + start = 0; + end = i; + ret = -ENOMEM; + goto free; + } + } + + read_lock_irqsave(&tasklist_lock, flags); + do_each_thread(g, t) { + if (start == end) { + ret = -EAGAIN; + goto unlock; + } + + if (t->ret_stack == NULL) { + t->curr_ret_stack = -1; + /* Make sure IRQs see the -1 first: */ + barrier(); + t->ret_stack = ret_stack_list[start++]; + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + } + } while_each_thread(g, t); + +unlock: + read_unlock_irqrestore(&tasklist_lock, flags); +free: + for (i = start; i < end; i++) + kfree(ret_stack_list[i]); + return ret; +} + +/* Allocate a return stack for each task */ +static int start_graph_tracing(void) +{ + struct ftrace_ret_stack **ret_stack_list; + int ret; + + ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE * + sizeof(struct ftrace_ret_stack *), + GFP_KERNEL); + + if (!ret_stack_list) + return -ENOMEM; + + do { + ret = alloc_retstack_tasklist(ret_stack_list); + } while (ret == -EAGAIN); + + kfree(ret_stack_list); + return ret; +} + +int register_ftrace_graph(trace_func_graph_ret_t retfunc, + trace_func_graph_ent_t entryfunc) +{ + int ret = 0; + + mutex_lock(&ftrace_sysctl_lock); + + atomic_inc(&ftrace_graph_active); + ret = start_graph_tracing(); + if (ret) { + atomic_dec(&ftrace_graph_active); + goto out; + } + + ftrace_graph_return = retfunc; + ftrace_graph_entry = entryfunc; + + ftrace_startup(FTRACE_START_FUNC_RET); + +out: + mutex_unlock(&ftrace_sysctl_lock); + return ret; +} + +void unregister_ftrace_graph(void) +{ + mutex_lock(&ftrace_sysctl_lock); + + atomic_dec(&ftrace_graph_active); + ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; + ftrace_graph_entry = ftrace_graph_entry_stub; + ftrace_shutdown(FTRACE_STOP_FUNC_RET); + + mutex_unlock(&ftrace_sysctl_lock); +} + +/* Allocate a return stack for newly created task */ +void ftrace_graph_init_task(struct task_struct *t) +{ + if (atomic_read(&ftrace_graph_active)) { + t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH + * sizeof(struct ftrace_ret_stack), + GFP_KERNEL); + if (!t->ret_stack) + return; + t->curr_ret_stack = -1; + atomic_set(&t->tracing_graph_pause, 0); + atomic_set(&t->trace_overrun, 0); + } else + t->ret_stack = NULL; +} + +void ftrace_graph_exit_task(struct task_struct *t) +{ + struct ftrace_ret_stack *ret_stack = t->ret_stack; + + t->ret_stack = NULL; + /* NULL must become visible to IRQs before we free it: */ + barrier(); + + kfree(ret_stack); +} + +void ftrace_graph_stop(void) +{ + ftrace_stop(); +} +#endif + diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 668bbb5..a9d9760 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -18,8 +18,46 @@ #include "trace.h" -/* Global flag to disable all recording to ring buffers */ -static int ring_buffers_off __read_mostly; +/* + * A fast way to enable or disable all ring buffers is to + * call tracing_on or tracing_off. Turning off the ring buffers + * prevents all ring buffers from being recorded to. + * Turning this switch on, makes it OK to write to the + * ring buffer, if the ring buffer is enabled itself. + * + * There's three layers that must be on in order to write + * to the ring buffer. + * + * 1) This global flag must be set. + * 2) The ring buffer must be enabled for recording. + * 3) The per cpu buffer must be enabled for recording. + * + * In case of an anomaly, this global flag has a bit set that + * will permantly disable all ring buffers. + */ + +/* + * Global flag to disable all recording to ring buffers + * This has two bits: ON, DISABLED + * + * ON DISABLED + * ---- ---------- + * 0 0 : ring buffers are off + * 1 0 : ring buffers are on + * X 1 : ring buffers are permanently disabled + */ + +enum { + RB_BUFFERS_ON_BIT = 0, + RB_BUFFERS_DISABLED_BIT = 1, +}; + +enum { + RB_BUFFERS_ON = 1 << RB_BUFFERS_ON_BIT, + RB_BUFFERS_DISABLED = 1 << RB_BUFFERS_DISABLED_BIT, +}; + +static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON; /** * tracing_on - enable all tracing buffers @@ -29,8 +67,9 @@ static int ring_buffers_off __read_mostly; */ void tracing_on(void) { - ring_buffers_off = 0; + set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); } +EXPORT_SYMBOL_GPL(tracing_on); /** * tracing_off - turn off all tracing buffers @@ -42,8 +81,22 @@ void tracing_on(void) */ void tracing_off(void) { - ring_buffers_off = 1; + clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags); } +EXPORT_SYMBOL_GPL(tracing_off); + +/** + * tracing_off_permanent - permanently disable ring buffers + * + * This function, once called, will disable all ring buffers + * permanenty. + */ +void tracing_off_permanent(void) +{ + set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags); +} + +#include "trace.h" /* Up this if you want to test the TIME_EXTENTS and normalization */ #define DEBUG_SHIFT 0 @@ -56,16 +109,18 @@ u64 ring_buffer_time_stamp(int cpu) preempt_disable_notrace(); /* shift to debug/test normalization and TIME_EXTENTS */ time = sched_clock() << DEBUG_SHIFT; - preempt_enable_notrace(); + preempt_enable_no_resched_notrace(); return time; } +EXPORT_SYMBOL_GPL(ring_buffer_time_stamp); void ring_buffer_normalize_time_stamp(int cpu, u64 *ts) { /* Just stupid testing the normalize function and deltas */ *ts >>= DEBUG_SHIFT; } +EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp); #define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event)) #define RB_ALIGNMENT_SHIFT 2 @@ -115,6 +170,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event) { return rb_event_length(event); } +EXPORT_SYMBOL_GPL(ring_buffer_event_length); /* inline for ring buffer fast paths */ static inline void * @@ -136,28 +192,33 @@ void *ring_buffer_event_data(struct ring_buffer_event *event) { return rb_event_data(event); } +EXPORT_SYMBOL_GPL(ring_buffer_event_data); #define for_each_buffer_cpu(buffer, cpu) \ - for_each_cpu_mask(cpu, buffer->cpumask) + for_each_cpu(cpu, buffer->cpumask) #define TS_SHIFT 27 #define TS_MASK ((1ULL << TS_SHIFT) - 1) #define TS_DELTA_TEST (~TS_MASK) -/* - * This hack stolen from mm/slob.c. - * We can store per page timing information in the page frame of the page. - * Thanks to Peter Zijlstra for suggesting this idea. - */ -struct buffer_page { +struct buffer_data_page { u64 time_stamp; /* page time stamp */ - local_t write; /* index for next write */ local_t commit; /* write commited index */ + unsigned char data[]; /* data of buffer page */ +}; + +struct buffer_page { + local_t write; /* index for next write */ unsigned read; /* index for next read */ struct list_head list; /* list of free pages */ - void *page; /* Actual data page */ + struct buffer_data_page *page; /* Actual data page */ }; +static void rb_init_page(struct buffer_data_page *bpage) +{ + local_set(&bpage->commit, 0); +} + /* * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing * this issue out. @@ -179,7 +240,7 @@ static inline int test_time_stamp(u64 delta) return 0; } -#define BUF_PAGE_SIZE PAGE_SIZE +#define BUF_PAGE_SIZE (PAGE_SIZE - sizeof(struct buffer_data_page)) /* * head_page == tail_page && head == tail then buffer is empty. @@ -187,7 +248,8 @@ static inline int test_time_stamp(u64 delta) struct ring_buffer_per_cpu { int cpu; struct ring_buffer *buffer; - spinlock_t lock; + spinlock_t reader_lock; /* serialize readers */ + raw_spinlock_t lock; struct lock_class_key lock_key; struct list_head pages; struct buffer_page *head_page; /* read from head */ @@ -202,11 +264,10 @@ struct ring_buffer_per_cpu { }; struct ring_buffer { - unsigned long size; unsigned pages; unsigned flags; int cpus; - cpumask_t cpumask; + cpumask_var_t cpumask; atomic_t record_disabled; struct mutex mutex; @@ -221,32 +282,16 @@ struct ring_buffer_iter { u64 read_stamp; }; +/* buffer may be either ring_buffer or ring_buffer_per_cpu */ #define RB_WARN_ON(buffer, cond) \ - do { \ - if (unlikely(cond)) { \ - atomic_inc(&buffer->record_disabled); \ - WARN_ON(1); \ - } \ - } while (0) - -#define RB_WARN_ON_RET(buffer, cond) \ - do { \ - if (unlikely(cond)) { \ - atomic_inc(&buffer->record_disabled); \ - WARN_ON(1); \ - return -1; \ - } \ - } while (0) - -#define RB_WARN_ON_ONCE(buffer, cond) \ - do { \ - static int once; \ - if (unlikely(cond) && !once) { \ - once++; \ + ({ \ + int _____ret = unlikely(cond); \ + if (_____ret) { \ atomic_inc(&buffer->record_disabled); \ WARN_ON(1); \ } \ - } while (0) + _____ret; \ + }) /** * check_pages - integrity check of buffer pages @@ -258,16 +303,20 @@ struct ring_buffer_iter { static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { struct list_head *head = &cpu_buffer->pages; - struct buffer_page *page, *tmp; + struct buffer_page *bpage, *tmp; - RB_WARN_ON_RET(cpu_buffer, head->next->prev != head); - RB_WARN_ON_RET(cpu_buffer, head->prev->next != head); + if (RB_WARN_ON(cpu_buffer, head->next->prev != head)) + return -1; + if (RB_WARN_ON(cpu_buffer, head->prev->next != head)) + return -1; - list_for_each_entry_safe(page, tmp, head, list) { - RB_WARN_ON_RET(cpu_buffer, - page->list.next->prev != &page->list); - RB_WARN_ON_RET(cpu_buffer, - page->list.prev->next != &page->list); + list_for_each_entry_safe(bpage, tmp, head, list) { + if (RB_WARN_ON(cpu_buffer, + bpage->list.next->prev != &bpage->list)) + return -1; + if (RB_WARN_ON(cpu_buffer, + bpage->list.prev->next != &bpage->list)) + return -1; } return 0; @@ -277,22 +326,23 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) { struct list_head *head = &cpu_buffer->pages; - struct buffer_page *page, *tmp; + struct buffer_page *bpage, *tmp; unsigned long addr; LIST_HEAD(pages); unsigned i; for (i = 0; i < nr_pages; i++) { - page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()), + bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu_buffer->cpu)); - if (!page) + if (!bpage) goto free_pages; - list_add(&page->list, &pages); + list_add(&bpage->list, &pages); addr = __get_free_page(GFP_KERNEL); if (!addr) goto free_pages; - page->page = (void *)addr; + bpage->page = (void *)addr; + rb_init_page(bpage->page); } list_splice(&pages, head); @@ -302,9 +352,9 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, return 0; free_pages: - list_for_each_entry_safe(page, tmp, &pages, list) { - list_del_init(&page->list); - free_buffer_page(page); + list_for_each_entry_safe(bpage, tmp, &pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); } return -ENOMEM; } @@ -313,7 +363,7 @@ static struct ring_buffer_per_cpu * rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; - struct buffer_page *page; + struct buffer_page *bpage; unsigned long addr; int ret; @@ -324,19 +374,21 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) cpu_buffer->cpu = cpu; cpu_buffer->buffer = buffer; - spin_lock_init(&cpu_buffer->lock); + spin_lock_init(&cpu_buffer->reader_lock); + cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; INIT_LIST_HEAD(&cpu_buffer->pages); - page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()), + bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); - if (!page) + if (!bpage) goto fail_free_buffer; - cpu_buffer->reader_page = page; + cpu_buffer->reader_page = bpage; addr = __get_free_page(GFP_KERNEL); if (!addr) goto fail_free_reader; - page->page = (void *)addr; + bpage->page = (void *)addr; + rb_init_page(bpage->page); INIT_LIST_HEAD(&cpu_buffer->reader_page->list); @@ -361,14 +413,14 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu) static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) { struct list_head *head = &cpu_buffer->pages; - struct buffer_page *page, *tmp; + struct buffer_page *bpage, *tmp; list_del_init(&cpu_buffer->reader_page->list); free_buffer_page(cpu_buffer->reader_page); - list_for_each_entry_safe(page, tmp, head, list) { - list_del_init(&page->list); - free_buffer_page(page); + list_for_each_entry_safe(bpage, tmp, head, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); } kfree(cpu_buffer); } @@ -381,7 +433,7 @@ extern int ring_buffer_page_too_big(void); /** * ring_buffer_alloc - allocate a new ring_buffer - * @size: the size in bytes that is needed. + * @size: the size in bytes per cpu that is needed. * @flags: attributes to set for the ring buffer. * * Currently the only flag that is available is the RB_FL_OVERWRITE @@ -406,6 +458,9 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags) if (!buffer) return NULL; + if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL)) + goto fail_free_buffer; + buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); buffer->flags = flags; @@ -413,14 +468,14 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags) if (buffer->pages == 1) buffer->pages++; - buffer->cpumask = cpu_possible_map; + cpumask_copy(buffer->cpumask, cpu_possible_mask); buffer->cpus = nr_cpu_ids; bsize = sizeof(void *) * nr_cpu_ids; buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()), GFP_KERNEL); if (!buffer->buffers) - goto fail_free_buffer; + goto fail_free_cpumask; for_each_buffer_cpu(buffer, cpu) { buffer->buffers[cpu] = @@ -440,10 +495,14 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags) } kfree(buffer->buffers); + fail_free_cpumask: + free_cpumask_var(buffer->cpumask); + fail_free_buffer: kfree(buffer); return NULL; } +EXPORT_SYMBOL_GPL(ring_buffer_alloc); /** * ring_buffer_free - free a ring buffer. @@ -457,15 +516,18 @@ ring_buffer_free(struct ring_buffer *buffer) for_each_buffer_cpu(buffer, cpu) rb_free_cpu_buffer(buffer->buffers[cpu]); + free_cpumask_var(buffer->cpumask); + kfree(buffer); } +EXPORT_SYMBOL_GPL(ring_buffer_free); static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer); static void rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) { - struct buffer_page *page; + struct buffer_page *bpage; struct list_head *p; unsigned i; @@ -473,13 +535,15 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages) synchronize_sched(); for (i = 0; i < nr_pages; i++) { - BUG_ON(list_empty(&cpu_buffer->pages)); + if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages))) + return; p = cpu_buffer->pages.next; - page = list_entry(p, struct buffer_page, list); - list_del_init(&page->list); - free_buffer_page(page); + bpage = list_entry(p, struct buffer_page, list); + list_del_init(&bpage->list); + free_buffer_page(bpage); } - BUG_ON(list_empty(&cpu_buffer->pages)); + if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages))) + return; rb_reset_cpu(cpu_buffer); @@ -493,7 +557,7 @@ static void rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, struct list_head *pages, unsigned nr_pages) { - struct buffer_page *page; + struct buffer_page *bpage; struct list_head *p; unsigned i; @@ -501,11 +565,12 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer, synchronize_sched(); for (i = 0; i < nr_pages; i++) { - BUG_ON(list_empty(pages)); + if (RB_WARN_ON(cpu_buffer, list_empty(pages))) + return; p = pages->next; - page = list_entry(p, struct buffer_page, list); - list_del_init(&page->list); - list_add_tail(&page->list, &cpu_buffer->pages); + bpage = list_entry(p, struct buffer_page, list); + list_del_init(&bpage->list); + list_add_tail(&bpage->list, &cpu_buffer->pages); } rb_reset_cpu(cpu_buffer); @@ -532,7 +597,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) { struct ring_buffer_per_cpu *cpu_buffer; unsigned nr_pages, rm_pages, new_pages; - struct buffer_page *page, *tmp; + struct buffer_page *bpage, *tmp; unsigned long buffer_size; unsigned long addr; LIST_HEAD(pages); @@ -562,7 +627,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) if (size < buffer_size) { /* easy case, just free pages */ - BUG_ON(nr_pages >= buffer->pages); + if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) { + mutex_unlock(&buffer->mutex); + return -1; + } rm_pages = buffer->pages - nr_pages; @@ -581,21 +649,26 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) * add these pages to the cpu_buffers. Otherwise we just free * them all and return -ENOMEM; */ - BUG_ON(nr_pages <= buffer->pages); + if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) { + mutex_unlock(&buffer->mutex); + return -1; + } + new_pages = nr_pages - buffer->pages; for_each_buffer_cpu(buffer, cpu) { for (i = 0; i < new_pages; i++) { - page = kzalloc_node(ALIGN(sizeof(*page), + bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); - if (!page) + if (!bpage) goto free_pages; - list_add(&page->list, &pages); + list_add(&bpage->list, &pages); addr = __get_free_page(GFP_KERNEL); if (!addr) goto free_pages; - page->page = (void *)addr; + bpage->page = (void *)addr; + rb_init_page(bpage->page); } } @@ -604,7 +677,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) rb_insert_pages(cpu_buffer, &pages, new_pages); } - BUG_ON(!list_empty(&pages)); + if (RB_WARN_ON(buffer, !list_empty(&pages))) { + mutex_unlock(&buffer->mutex); + return -1; + } out: buffer->pages = nr_pages; @@ -613,22 +689,29 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size) return size; free_pages: - list_for_each_entry_safe(page, tmp, &pages, list) { - list_del_init(&page->list); - free_buffer_page(page); + list_for_each_entry_safe(bpage, tmp, &pages, list) { + list_del_init(&bpage->list); + free_buffer_page(bpage); } mutex_unlock(&buffer->mutex); return -ENOMEM; } +EXPORT_SYMBOL_GPL(ring_buffer_resize); static inline int rb_null_event(struct ring_buffer_event *event) { return event->type == RINGBUF_TYPE_PADDING; } -static inline void *__rb_page_index(struct buffer_page *page, unsigned index) +static inline void * +__rb_data_page_index(struct buffer_data_page *bpage, unsigned index) +{ + return bpage->data + index; +} + +static inline void *__rb_page_index(struct buffer_page *bpage, unsigned index) { - return page->page + index; + return bpage->page->data + index; } static inline struct ring_buffer_event * @@ -658,7 +741,7 @@ static inline unsigned rb_page_write(struct buffer_page *bpage) static inline unsigned rb_page_commit(struct buffer_page *bpage) { - return local_read(&bpage->commit); + return local_read(&bpage->page->commit); } /* Size is determined by what has been commited */ @@ -693,7 +776,8 @@ static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer) head += rb_event_length(event)) { event = __rb_page_index(cpu_buffer->head_page, head); - BUG_ON(rb_null_event(event)); + if (RB_WARN_ON(cpu_buffer, rb_null_event(event))) + return; /* Only count data entries */ if (event->type != RINGBUF_TYPE_DATA) continue; @@ -703,14 +787,14 @@ static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer) } static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer, - struct buffer_page **page) + struct buffer_page **bpage) { - struct list_head *p = (*page)->list.next; + struct list_head *p = (*bpage)->list.next; if (p == &cpu_buffer->pages) p = p->next; - *page = list_entry(p, struct buffer_page, list); + *bpage = list_entry(p, struct buffer_page, list); } static inline unsigned @@ -746,16 +830,18 @@ rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer, addr &= PAGE_MASK; while (cpu_buffer->commit_page->page != (void *)addr) { - RB_WARN_ON(cpu_buffer, - cpu_buffer->commit_page == cpu_buffer->tail_page); - cpu_buffer->commit_page->commit = + if (RB_WARN_ON(cpu_buffer, + cpu_buffer->commit_page == cpu_buffer->tail_page)) + return; + cpu_buffer->commit_page->page->commit = cpu_buffer->commit_page->write; rb_inc_page(cpu_buffer, &cpu_buffer->commit_page); - cpu_buffer->write_stamp = cpu_buffer->commit_page->time_stamp; + cpu_buffer->write_stamp = + cpu_buffer->commit_page->page->time_stamp; } /* Now set the commit to the event's index */ - local_set(&cpu_buffer->commit_page->commit, index); + local_set(&cpu_buffer->commit_page->page->commit, index); } static inline void @@ -769,25 +855,38 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer) * back to us). This allows us to do a simple loop to * assign the commit to the tail. */ + again: while (cpu_buffer->commit_page != cpu_buffer->tail_page) { - cpu_buffer->commit_page->commit = + cpu_buffer->commit_page->page->commit = cpu_buffer->commit_page->write; rb_inc_page(cpu_buffer, &cpu_buffer->commit_page); - cpu_buffer->write_stamp = cpu_buffer->commit_page->time_stamp; + cpu_buffer->write_stamp = + cpu_buffer->commit_page->page->time_stamp; /* add barrier to keep gcc from optimizing too much */ barrier(); } while (rb_commit_index(cpu_buffer) != rb_page_write(cpu_buffer->commit_page)) { - cpu_buffer->commit_page->commit = + cpu_buffer->commit_page->page->commit = cpu_buffer->commit_page->write; barrier(); } + + /* again, keep gcc from optimizing */ + barrier(); + + /* + * If an interrupt came in just after the first while loop + * and pushed the tail page forward, we will be left with + * a dangling commit that will never go forward. + */ + if (unlikely(cpu_buffer->commit_page != cpu_buffer->tail_page)) + goto again; } static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer) { - cpu_buffer->read_stamp = cpu_buffer->reader_page->time_stamp; + cpu_buffer->read_stamp = cpu_buffer->reader_page->page->time_stamp; cpu_buffer->reader_page->read = 0; } @@ -806,7 +905,7 @@ static inline void rb_inc_iter(struct ring_buffer_iter *iter) else rb_inc_page(cpu_buffer, &iter->head_page); - iter->read_stamp = iter->head_page->time_stamp; + iter->read_stamp = iter->head_page->page->time_stamp; iter->head = 0; } @@ -880,12 +979,15 @@ static struct ring_buffer_event * __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, unsigned type, unsigned long length, u64 *ts) { - struct buffer_page *tail_page, *head_page, *reader_page; + struct buffer_page *tail_page, *head_page, *reader_page, *commit_page; unsigned long tail, write; struct ring_buffer *buffer = cpu_buffer->buffer; struct ring_buffer_event *event; unsigned long flags; + commit_page = cpu_buffer->commit_page; + /* we just need to protect against interrupts */ + barrier(); tail_page = cpu_buffer->tail_page; write = local_add_return(length, &tail_page->write); tail = write - length; @@ -894,7 +996,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, if (write > BUF_PAGE_SIZE) { struct buffer_page *next_page = tail_page; - spin_lock_irqsave(&cpu_buffer->lock, flags); + local_irq_save(flags); + __raw_spin_lock(&cpu_buffer->lock); rb_inc_page(cpu_buffer, &next_page); @@ -902,14 +1005,15 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, reader_page = cpu_buffer->reader_page; /* we grabbed the lock before incrementing */ - RB_WARN_ON(cpu_buffer, next_page == reader_page); + if (RB_WARN_ON(cpu_buffer, next_page == reader_page)) + goto out_unlock; /* * If for some reason, we had an interrupt storm that made * it all the way around the buffer, bail, and warn * about it. */ - if (unlikely(next_page == cpu_buffer->commit_page)) { + if (unlikely(next_page == commit_page)) { WARN_ON_ONCE(1); goto out_unlock; } @@ -940,12 +1044,12 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, */ if (tail_page == cpu_buffer->tail_page) { local_set(&next_page->write, 0); - local_set(&next_page->commit, 0); + local_set(&next_page->page->commit, 0); cpu_buffer->tail_page = next_page; /* reread the time stamp */ *ts = ring_buffer_time_stamp(cpu_buffer->cpu); - cpu_buffer->tail_page->time_stamp = *ts; + cpu_buffer->tail_page->page->time_stamp = *ts; } /* @@ -970,7 +1074,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, rb_set_commit_to_write(cpu_buffer); } - spin_unlock_irqrestore(&cpu_buffer->lock, flags); + __raw_spin_unlock(&cpu_buffer->lock); + local_irq_restore(flags); /* fail and let the caller try again */ return ERR_PTR(-EAGAIN); @@ -978,7 +1083,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* We reserved something on the buffer */ - BUG_ON(write > BUF_PAGE_SIZE); + if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE)) + return NULL; event = __rb_page_index(tail_page, tail); rb_update_event(event, type, length); @@ -988,12 +1094,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, * this page's time stamp. */ if (!tail && rb_is_commit(cpu_buffer, event)) - cpu_buffer->commit_page->time_stamp = *ts; + cpu_buffer->commit_page->page->time_stamp = *ts; return event; out_unlock: - spin_unlock_irqrestore(&cpu_buffer->lock, flags); + __raw_spin_unlock(&cpu_buffer->lock); + local_irq_restore(flags); return NULL; } @@ -1038,7 +1145,7 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, event->time_delta = *delta & TS_MASK; event->array[0] = *delta >> TS_SHIFT; } else { - cpu_buffer->commit_page->time_stamp = *ts; + cpu_buffer->commit_page->page->time_stamp = *ts; event->time_delta = 0; event->array[0] = 0; } @@ -1076,10 +1183,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, * storm or we have something buggy. * Bail! */ - if (unlikely(++nr_loops > 1000)) { - RB_WARN_ON(cpu_buffer, 1); + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000)) return NULL; - } ts = ring_buffer_time_stamp(cpu_buffer->cpu); @@ -1175,19 +1280,18 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, struct ring_buffer_event *event; int cpu, resched; - if (ring_buffers_off) + if (ring_buffer_flags != RB_BUFFERS_ON) return NULL; if (atomic_read(&buffer->record_disabled)) return NULL; /* If we are tracing schedule, we don't want to recurse */ - resched = need_resched(); - preempt_disable_notrace(); + resched = ftrace_preempt_disable(); cpu = raw_smp_processor_id(); - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) goto out; cpu_buffer = buffer->buffers[cpu]; @@ -1214,12 +1318,10 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, return event; out: - if (resched) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); + ftrace_preempt_enable(resched); return NULL; } +EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve); static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) @@ -1259,16 +1361,14 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer, /* * Only the last preempt count needs to restore preemption. */ - if (preempt_count() == 1) { - if (per_cpu(rb_need_resched, cpu)) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); - } else + if (preempt_count() == 1) + ftrace_preempt_enable(per_cpu(rb_need_resched, cpu)); + else preempt_enable_no_resched_notrace(); return 0; } +EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit); /** * ring_buffer_write - write data to the buffer without reserving @@ -1294,18 +1394,17 @@ int ring_buffer_write(struct ring_buffer *buffer, int ret = -EBUSY; int cpu, resched; - if (ring_buffers_off) + if (ring_buffer_flags != RB_BUFFERS_ON) return -EBUSY; if (atomic_read(&buffer->record_disabled)) return -EBUSY; - resched = need_resched(); - preempt_disable_notrace(); + resched = ftrace_preempt_disable(); cpu = raw_smp_processor_id(); - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) goto out; cpu_buffer = buffer->buffers[cpu]; @@ -1327,13 +1426,11 @@ int ring_buffer_write(struct ring_buffer *buffer, ret = 0; out: - if (resched) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); + ftrace_preempt_enable(resched); return ret; } +EXPORT_SYMBOL_GPL(ring_buffer_write); static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) { @@ -1360,6 +1457,7 @@ void ring_buffer_record_disable(struct ring_buffer *buffer) { atomic_inc(&buffer->record_disabled); } +EXPORT_SYMBOL_GPL(ring_buffer_record_disable); /** * ring_buffer_record_enable - enable writes to the buffer @@ -1372,6 +1470,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer) { atomic_dec(&buffer->record_disabled); } +EXPORT_SYMBOL_GPL(ring_buffer_record_enable); /** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer @@ -1387,12 +1486,13 @@ void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; cpu_buffer = buffer->buffers[cpu]; atomic_inc(&cpu_buffer->record_disabled); } +EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu); /** * ring_buffer_record_enable_cpu - enable writes to the buffer @@ -1406,12 +1506,13 @@ void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; cpu_buffer = buffer->buffers[cpu]; atomic_dec(&cpu_buffer->record_disabled); } +EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu); /** * ring_buffer_entries_cpu - get the number of entries in a cpu buffer @@ -1422,12 +1523,13 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; return cpu_buffer->entries; } +EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu); /** * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer @@ -1438,12 +1540,13 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 0; cpu_buffer = buffer->buffers[cpu]; return cpu_buffer->overrun; } +EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu); /** * ring_buffer_entries - get the number of entries in a buffer @@ -1466,6 +1569,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer) return entries; } +EXPORT_SYMBOL_GPL(ring_buffer_entries); /** * ring_buffer_overrun_cpu - get the number of overruns in buffer @@ -1488,15 +1592,9 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer) return overruns; } +EXPORT_SYMBOL_GPL(ring_buffer_overruns); -/** - * ring_buffer_iter_reset - reset an iterator - * @iter: The iterator to reset - * - * Resets the iterator, so that it will start from the beginning - * again. - */ -void ring_buffer_iter_reset(struct ring_buffer_iter *iter) +static void rb_iter_reset(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; @@ -1511,10 +1609,28 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter) if (iter->head) iter->read_stamp = cpu_buffer->read_stamp; else - iter->read_stamp = iter->head_page->time_stamp; + iter->read_stamp = iter->head_page->page->time_stamp; } /** + * ring_buffer_iter_reset - reset an iterator + * @iter: The iterator to reset + * + * Resets the iterator, so that it will start from the beginning + * again. + */ +void ring_buffer_iter_reset(struct ring_buffer_iter *iter) +{ + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + unsigned long flags; + + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + rb_iter_reset(iter); + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); +} +EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); + +/** * ring_buffer_iter_empty - check if an iterator has no more to read * @iter: The iterator to check */ @@ -1527,6 +1643,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) return iter->head_page == cpu_buffer->commit_page && iter->head == rb_commit_index(cpu_buffer); } +EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); static void rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, @@ -1597,7 +1714,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) unsigned long flags; int nr_loops = 0; - spin_lock_irqsave(&cpu_buffer->lock, flags); + local_irq_save(flags); + __raw_spin_lock(&cpu_buffer->lock); again: /* @@ -1606,8 +1724,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) * a case where we will loop three times. There should be no * reason to loop four times (that I know of). */ - if (unlikely(++nr_loops > 3)) { - RB_WARN_ON(cpu_buffer, 1); + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) { reader = NULL; goto out; } @@ -1619,8 +1736,9 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) goto out; /* Never should we have an index greater than the size */ - RB_WARN_ON(cpu_buffer, - cpu_buffer->reader_page->read > rb_page_size(reader)); + if (RB_WARN_ON(cpu_buffer, + cpu_buffer->reader_page->read > rb_page_size(reader))) + goto out; /* check if we caught up to the tail */ reader = NULL; @@ -1637,7 +1755,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->list.prev = reader->list.prev; local_set(&cpu_buffer->reader_page->write, 0); - local_set(&cpu_buffer->reader_page->commit, 0); + local_set(&cpu_buffer->reader_page->page->commit, 0); /* Make the reader page now replace the head */ reader->list.prev->next = &cpu_buffer->reader_page->list; @@ -1659,7 +1777,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) goto again; out: - spin_unlock_irqrestore(&cpu_buffer->lock, flags); + __raw_spin_unlock(&cpu_buffer->lock); + local_irq_restore(flags); return reader; } @@ -1673,7 +1792,8 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) reader = rb_get_reader_page(cpu_buffer); /* This function should not be called when buffer is empty */ - BUG_ON(!reader); + if (RB_WARN_ON(cpu_buffer, !reader)) + return; event = rb_reader_event(cpu_buffer); @@ -1700,7 +1820,9 @@ static void rb_advance_iter(struct ring_buffer_iter *iter) * Check if we are at the end of the buffer. */ if (iter->head >= rb_page_size(iter->head_page)) { - BUG_ON(iter->head_page == cpu_buffer->commit_page); + if (RB_WARN_ON(buffer, + iter->head_page == cpu_buffer->commit_page)) + return; rb_inc_iter(iter); return; } @@ -1713,8 +1835,10 @@ static void rb_advance_iter(struct ring_buffer_iter *iter) * This should not be called to advance the header if we are * at the tail of the buffer. */ - BUG_ON((iter->head_page == cpu_buffer->commit_page) && - (iter->head + length > rb_commit_index(cpu_buffer))); + if (RB_WARN_ON(cpu_buffer, + (iter->head_page == cpu_buffer->commit_page) && + (iter->head + length > rb_commit_index(cpu_buffer)))) + return; rb_update_iter_read_stamp(iter, event); @@ -1726,24 +1850,15 @@ static void rb_advance_iter(struct ring_buffer_iter *iter) rb_advance_iter(iter); } -/** - * ring_buffer_peek - peek at the next event to be read - * @buffer: The ring buffer to read - * @cpu: The cpu to peak at - * @ts: The timestamp counter of this event. - * - * This will return the event that will be read next, but does - * not consume the data. - */ -struct ring_buffer_event * -ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) +static struct ring_buffer_event * +rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; struct buffer_page *reader; int nr_loops = 0; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; cpu_buffer = buffer->buffers[cpu]; @@ -1757,10 +1872,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) * can have. Nesting 10 deep of interrupts is clearly * an anomaly. */ - if (unlikely(++nr_loops > 10)) { - RB_WARN_ON(cpu_buffer, 1); + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10)) return NULL; - } reader = rb_get_reader_page(cpu_buffer); if (!reader) @@ -1797,17 +1910,10 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) return NULL; } +EXPORT_SYMBOL_GPL(ring_buffer_peek); -/** - * ring_buffer_iter_peek - peek at the next event to be read - * @iter: The ring buffer iterator - * @ts: The timestamp counter of this event. - * - * This will return the event that will be read next, but does - * not increment the iterator. - */ -struct ring_buffer_event * -ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) +static struct ring_buffer_event * +rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) { struct ring_buffer *buffer; struct ring_buffer_per_cpu *cpu_buffer; @@ -1829,10 +1935,8 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) * can have. Nesting 10 deep of interrupts is clearly * an anomaly. */ - if (unlikely(++nr_loops > 10)) { - RB_WARN_ON(cpu_buffer, 1); + if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10)) return NULL; - } if (rb_per_cpu_empty(cpu_buffer)) return NULL; @@ -1867,6 +1971,52 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return NULL; } +EXPORT_SYMBOL_GPL(ring_buffer_iter_peek); + +/** + * ring_buffer_peek - peek at the next event to be read + * @buffer: The ring buffer to read + * @cpu: The cpu to peak at + * @ts: The timestamp counter of this event. + * + * This will return the event that will be read next, but does + * not consume the data. + */ +struct ring_buffer_event * +ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_event *event; + unsigned long flags; + + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + event = rb_buffer_peek(buffer, cpu, ts); + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + return event; +} + +/** + * ring_buffer_iter_peek - peek at the next event to be read + * @iter: The ring buffer iterator + * @ts: The timestamp counter of this event. + * + * This will return the event that will be read next, but does + * not increment the iterator. + */ +struct ring_buffer_event * +ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) +{ + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + struct ring_buffer_event *event; + unsigned long flags; + + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + event = rb_iter_peek(iter, ts); + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + return event; +} /** * ring_buffer_consume - return an event and consume it @@ -1879,21 +2029,27 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_event * ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) { - struct ring_buffer_per_cpu *cpu_buffer; + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct ring_buffer_event *event; + unsigned long flags; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; - event = ring_buffer_peek(buffer, cpu, ts); + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + event = rb_buffer_peek(buffer, cpu, ts); if (!event) - return NULL; + goto out; - cpu_buffer = buffer->buffers[cpu]; rb_advance_reader(cpu_buffer); + out: + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + return event; } +EXPORT_SYMBOL_GPL(ring_buffer_consume); /** * ring_buffer_read_start - start a non consuming read of the buffer @@ -1914,7 +2070,7 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu) struct ring_buffer_iter *iter; unsigned long flags; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; iter = kmalloc(sizeof(*iter), GFP_KERNEL); @@ -1928,12 +2084,15 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu) atomic_inc(&cpu_buffer->record_disabled); synchronize_sched(); - spin_lock_irqsave(&cpu_buffer->lock, flags); - ring_buffer_iter_reset(iter); - spin_unlock_irqrestore(&cpu_buffer->lock, flags); + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + __raw_spin_lock(&cpu_buffer->lock); + rb_iter_reset(iter); + __raw_spin_unlock(&cpu_buffer->lock); + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); return iter; } +EXPORT_SYMBOL_GPL(ring_buffer_read_start); /** * ring_buffer_finish - finish reading the iterator of the buffer @@ -1950,6 +2109,7 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter) atomic_dec(&cpu_buffer->record_disabled); kfree(iter); } +EXPORT_SYMBOL_GPL(ring_buffer_read_finish); /** * ring_buffer_read - read the next item in the ring buffer by the iterator @@ -1962,15 +2122,21 @@ struct ring_buffer_event * ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) { struct ring_buffer_event *event; + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + unsigned long flags; - event = ring_buffer_iter_peek(iter, ts); + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + event = rb_iter_peek(iter, ts); if (!event) - return NULL; + goto out; rb_advance_iter(iter); + out: + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); return event; } +EXPORT_SYMBOL_GPL(ring_buffer_read); /** * ring_buffer_size - return the size of the ring buffer (in bytes) @@ -1980,6 +2146,7 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer) { return BUF_PAGE_SIZE * buffer->pages; } +EXPORT_SYMBOL_GPL(ring_buffer_size); static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) @@ -1987,7 +2154,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->head_page = list_entry(cpu_buffer->pages.next, struct buffer_page, list); local_set(&cpu_buffer->head_page->write, 0); - local_set(&cpu_buffer->head_page->commit, 0); + local_set(&cpu_buffer->head_page->page->commit, 0); cpu_buffer->head_page->read = 0; @@ -1996,7 +2163,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) INIT_LIST_HEAD(&cpu_buffer->reader_page->list); local_set(&cpu_buffer->reader_page->write, 0); - local_set(&cpu_buffer->reader_page->commit, 0); + local_set(&cpu_buffer->reader_page->page->commit, 0); cpu_buffer->reader_page->read = 0; cpu_buffer->overrun = 0; @@ -2013,15 +2180,20 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; unsigned long flags; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; - spin_lock_irqsave(&cpu_buffer->lock, flags); + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + __raw_spin_lock(&cpu_buffer->lock); rb_reset_cpu(cpu_buffer); - spin_unlock_irqrestore(&cpu_buffer->lock, flags); + __raw_spin_unlock(&cpu_buffer->lock); + + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } +EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); /** * ring_buffer_reset - reset a ring buffer @@ -2034,6 +2206,7 @@ void ring_buffer_reset(struct ring_buffer *buffer) for_each_buffer_cpu(buffer, cpu) ring_buffer_reset_cpu(buffer, cpu); } +EXPORT_SYMBOL_GPL(ring_buffer_reset); /** * rind_buffer_empty - is the ring buffer empty? @@ -2052,6 +2225,7 @@ int ring_buffer_empty(struct ring_buffer *buffer) } return 1; } +EXPORT_SYMBOL_GPL(ring_buffer_empty); /** * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty? @@ -2062,12 +2236,13 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; - if (!cpu_isset(cpu, buffer->cpumask)) + if (!cpumask_test_cpu(cpu, buffer->cpumask)) return 1; cpu_buffer = buffer->buffers[cpu]; return rb_per_cpu_empty(cpu_buffer); } +EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu); /** * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers @@ -2085,13 +2260,12 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, struct ring_buffer_per_cpu *cpu_buffer_a; struct ring_buffer_per_cpu *cpu_buffer_b; - if (!cpu_isset(cpu, buffer_a->cpumask) || - !cpu_isset(cpu, buffer_b->cpumask)) + if (!cpumask_test_cpu(cpu, buffer_a->cpumask) || + !cpumask_test_cpu(cpu, buffer_b->cpumask)) return -EINVAL; /* At least make sure the two buffers are somewhat the same */ - if (buffer_a->size != buffer_b->size || - buffer_a->pages != buffer_b->pages) + if (buffer_a->pages != buffer_b->pages) return -EINVAL; cpu_buffer_a = buffer_a->buffers[cpu]; @@ -2117,17 +2291,180 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, return 0; } +EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); + +static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer, + struct buffer_data_page *bpage) +{ + struct ring_buffer_event *event; + unsigned long head; + + __raw_spin_lock(&cpu_buffer->lock); + for (head = 0; head < local_read(&bpage->commit); + head += rb_event_length(event)) { + + event = __rb_data_page_index(bpage, head); + if (RB_WARN_ON(cpu_buffer, rb_null_event(event))) + return; + /* Only count data entries */ + if (event->type != RINGBUF_TYPE_DATA) + continue; + cpu_buffer->entries--; + } + __raw_spin_unlock(&cpu_buffer->lock); +} + +/** + * ring_buffer_alloc_read_page - allocate a page to read from buffer + * @buffer: the buffer to allocate for. + * + * This function is used in conjunction with ring_buffer_read_page. + * When reading a full page from the ring buffer, these functions + * can be used to speed up the process. The calling function should + * allocate a few pages first with this function. Then when it + * needs to get pages from the ring buffer, it passes the result + * of this function into ring_buffer_read_page, which will swap + * the page that was allocated, with the read page of the buffer. + * + * Returns: + * The page allocated, or NULL on error. + */ +void *ring_buffer_alloc_read_page(struct ring_buffer *buffer) +{ + unsigned long addr; + struct buffer_data_page *bpage; + + addr = __get_free_page(GFP_KERNEL); + if (!addr) + return NULL; + + bpage = (void *)addr; + + return bpage; +} + +/** + * ring_buffer_free_read_page - free an allocated read page + * @buffer: the buffer the page was allocate for + * @data: the page to free + * + * Free a page allocated from ring_buffer_alloc_read_page. + */ +void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data) +{ + free_page((unsigned long)data); +} + +/** + * ring_buffer_read_page - extract a page from the ring buffer + * @buffer: buffer to extract from + * @data_page: the page to use allocated from ring_buffer_alloc_read_page + * @cpu: the cpu of the buffer to extract + * @full: should the extraction only happen when the page is full. + * + * This function will pull out a page from the ring buffer and consume it. + * @data_page must be the address of the variable that was returned + * from ring_buffer_alloc_read_page. This is because the page might be used + * to swap with a page in the ring buffer. + * + * for example: + * rpage = ring_buffer_alloc_page(buffer); + * if (!rpage) + * return error; + * ret = ring_buffer_read_page(buffer, &rpage, cpu, 0); + * if (ret) + * process_page(rpage); + * + * When @full is set, the function will not return true unless + * the writer is off the reader page. + * + * Note: it is up to the calling functions to handle sleeps and wakeups. + * The ring buffer can be used anywhere in the kernel and can not + * blindly call wake_up. The layer that uses the ring buffer must be + * responsible for that. + * + * Returns: + * 1 if data has been transferred + * 0 if no data has been transferred. + */ +int ring_buffer_read_page(struct ring_buffer *buffer, + void **data_page, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_event *event; + struct buffer_data_page *bpage; + unsigned long flags; + int ret = 0; + + if (!data_page) + return 0; + + bpage = *data_page; + if (!bpage) + return 0; + + spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + /* + * rb_buffer_peek will get the next ring buffer if + * the current reader page is empty. + */ + event = rb_buffer_peek(buffer, cpu, NULL); + if (!event) + goto out; + + /* check for data */ + if (!local_read(&cpu_buffer->reader_page->page->commit)) + goto out; + /* + * If the writer is already off of the read page, then simply + * switch the read page with the given page. Otherwise + * we need to copy the data from the reader to the writer. + */ + if (cpu_buffer->reader_page == cpu_buffer->commit_page) { + unsigned int read = cpu_buffer->reader_page->read; + + if (full) + goto out; + /* The writer is still on the reader page, we must copy */ + bpage = cpu_buffer->reader_page->page; + memcpy(bpage->data, + cpu_buffer->reader_page->page->data + read, + local_read(&bpage->commit) - read); + + /* consume what was read */ + cpu_buffer->reader_page += read; + + } else { + /* swap the pages */ + rb_init_page(bpage); + bpage = cpu_buffer->reader_page->page; + cpu_buffer->reader_page->page = *data_page; + cpu_buffer->reader_page->read = 0; + *data_page = bpage; + } + ret = 1; + + /* update the entry counter */ + rb_remove_entries(cpu_buffer, bpage); + out: + spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + return ret; +} static ssize_t rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - int *p = filp->private_data; + long *p = filp->private_data; char buf[64]; int r; - /* !ring_buffers_off == tracing_on */ - r = sprintf(buf, "%d\n", !*p); + if (test_bit(RB_BUFFERS_DISABLED_BIT, p)) + r = sprintf(buf, "permanently disabled\n"); + else + r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p)); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } @@ -2136,7 +2473,7 @@ static ssize_t rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - int *p = filp->private_data; + long *p = filp->private_data; char buf[64]; long val; int ret; @@ -2153,8 +2490,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf, if (ret < 0) return ret; - /* !ring_buffers_off == tracing_on */ - *p = !val; + if (val) + set_bit(RB_BUFFERS_ON_BIT, p); + else + clear_bit(RB_BUFFERS_ON_BIT, p); (*ppos)++; @@ -2176,7 +2515,7 @@ static __init int rb_init_debugfs(void) d_tracer = tracing_init_dentry(); entry = debugfs_create_file("tracing_on", 0644, d_tracer, - &ring_buffers_off, &rb_simple_fops); + &ring_buffer_flags, &rb_simple_fops); if (!entry) pr_warning("Could not create debugfs 'tracing_on' entry\n"); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d86e325..c580233 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -43,6 +43,38 @@ unsigned long __read_mostly tracing_max_latency = (cycle_t)ULONG_MAX; unsigned long __read_mostly tracing_thresh; +/* + * We need to change this state when a selftest is running. + * A selftest will lurk into the ring-buffer to count the + * entries inserted during the selftest although some concurrent + * insertions into the ring-buffer such as ftrace_printk could occurred + * at the same time, giving false positive or negative results. + */ +static bool __read_mostly tracing_selftest_running; + +/* For tracers that don't implement custom flags */ +static struct tracer_opt dummy_tracer_opt[] = { + { } +}; + +static struct tracer_flags dummy_tracer_flags = { + .val = 0, + .opts = dummy_tracer_opt +}; + +static int dummy_set_flag(u32 old_flags, u32 bit, int set) +{ + return 0; +} + +/* + * Kill all tracing for good (never come back). + * It is initialized to 1 but will turn to zero if the initialization + * of the tracer is successful. But that is the only place that sets + * this back to zero. + */ +int tracing_disabled = 1; + static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled); static inline void ftrace_disable_cpu(void) @@ -57,12 +89,41 @@ static inline void ftrace_enable_cpu(void) preempt_enable(); } -static cpumask_t __read_mostly tracing_buffer_mask; +static cpumask_var_t __read_mostly tracing_buffer_mask; #define for_each_tracing_cpu(cpu) \ - for_each_cpu_mask(cpu, tracing_buffer_mask) + for_each_cpu(cpu, tracing_buffer_mask) + +/* + * ftrace_dump_on_oops - variable to dump ftrace buffer on oops + * + * If there is an oops (or kernel panic) and the ftrace_dump_on_oops + * is set, then ftrace_dump is called. This will output the contents + * of the ftrace buffers to the console. This is very useful for + * capturing traces that lead to crashes and outputing it to a + * serial console. + * + * It is default off, but you can enable it with either specifying + * "ftrace_dump_on_oops" in the kernel command line, or setting + * /proc/sys/kernel/ftrace_dump_on_oops to true. + */ +int ftrace_dump_on_oops; -static int tracing_disabled = 1; +static int tracing_set_tracer(char *buf); + +static int __init set_ftrace(char *str) +{ + tracing_set_tracer(str); + return 1; +} +__setup("ftrace", set_ftrace); + +static int __init set_ftrace_dump_on_oops(char *str) +{ + ftrace_dump_on_oops = 1; + return 1; +} +__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); long ns2usecs(cycle_t nsec) @@ -112,6 +173,19 @@ static DEFINE_PER_CPU(struct trace_array_cpu, max_data); /* tracer_enabled is used to toggle activation of a tracer */ static int tracer_enabled = 1; +/** + * tracing_is_enabled - return tracer_enabled status + * + * This function is used by other tracers to know the status + * of the tracer_enabled flag. Tracers may use this function + * to know if it should enable their features when starting + * up. See irqsoff tracer for an example (start_irqsoff_tracer). + */ +int tracing_is_enabled(void) +{ + return tracer_enabled; +} + /* function tracing enabled */ int ftrace_function_enabled; @@ -153,8 +227,9 @@ static DEFINE_MUTEX(trace_types_lock); /* trace_wait is a waitqueue for tasks blocked on trace_poll */ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); -/* trace_flags holds iter_ctrl options */ -unsigned long trace_flags = TRACE_ITER_PRINT_PARENT; +/* trace_flags holds trace_options default values */ +unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | + TRACE_ITER_ANNOTATE; /** * trace_wake_up - wake up tasks waiting for trace input @@ -193,13 +268,6 @@ unsigned long nsecs_to_usecs(unsigned long nsecs) return nsecs / 1000; } -/* - * TRACE_ITER_SYM_MASK masks the options in trace_flags that - * control the output of kernel symbols. - */ -#define TRACE_ITER_SYM_MASK \ - (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR) - /* These must match the bit postions in trace_iterator_flags */ static const char *trace_options[] = { "print-parent", @@ -213,6 +281,12 @@ static const char *trace_options[] = { "stacktrace", "sched-tree", "ftrace_printk", + "ftrace_preempt", + "branch", + "annotate", + "userstacktrace", + "sym-userobj", + "printk-msg-only", NULL }; @@ -246,7 +320,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) memcpy(data->comm, tsk->comm, TASK_COMM_LEN); data->pid = tsk->pid; - data->uid = tsk->uid; + data->uid = task_uid(tsk); data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; data->policy = tsk->policy; data->rt_priority = tsk->rt_priority; @@ -359,6 +433,28 @@ trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len) return trace_seq_putmem(s, hex, j); } +static int +trace_seq_path(struct trace_seq *s, struct path *path) +{ + unsigned char *p; + + if (s->len >= (PAGE_SIZE - 1)) + return 0; + p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); + if (!IS_ERR(p)) { + p = mangle_path(s->buffer + s->len, p, "\n"); + if (p) { + s->len = p - s->buffer; + return 1; + } + } else { + s->buffer[s->len++] = '?'; + return 1; + } + + return 0; +} + static void trace_seq_reset(struct trace_seq *s) { @@ -470,7 +566,17 @@ int register_tracer(struct tracer *type) return -1; } + /* + * When this gets called we hold the BKL which means that + * preemption is disabled. Various trace selftests however + * need to disable and enable preemption for successful tests. + * So we drop the BKL here and grab it after the tests again. + */ + unlock_kernel(); mutex_lock(&trace_types_lock); + + tracing_selftest_running = true; + for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ @@ -481,12 +587,20 @@ int register_tracer(struct tracer *type) } } + if (!type->set_flag) + type->set_flag = &dummy_set_flag; + if (!type->flags) + type->flags = &dummy_tracer_flags; + else + if (!type->flags->opts) + type->flags->opts = dummy_tracer_opt; + #ifdef CONFIG_FTRACE_STARTUP_TEST if (type->selftest) { struct tracer *saved_tracer = current_trace; struct trace_array *tr = &global_trace; - int saved_ctrl = tr->ctrl; int i; + /* * Run a selftest on this tracer. * Here we reset the trace buffer, and set the current @@ -494,25 +608,23 @@ int register_tracer(struct tracer *type) * internal tracing to verify that everything is in order. * If we fail, we do not register this tracer. */ - for_each_tracing_cpu(i) { + for_each_tracing_cpu(i) tracing_reset(tr, i); - } + current_trace = type; - tr->ctrl = 0; /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); ret = type->selftest(type, tr); /* the test is responsible for resetting too */ current_trace = saved_tracer; - tr->ctrl = saved_ctrl; if (ret) { printk(KERN_CONT "FAILED!\n"); goto out; } /* Only reset on passing, to avoid touching corrupted buffers */ - for_each_tracing_cpu(i) { + for_each_tracing_cpu(i) tracing_reset(tr, i); - } + printk(KERN_CONT "PASSED\n"); } #endif @@ -524,7 +636,9 @@ int register_tracer(struct tracer *type) max_tracer_type_len = len; out: + tracing_selftest_running = false; mutex_unlock(&trace_types_lock); + lock_kernel(); return ret; } @@ -564,6 +678,16 @@ void tracing_reset(struct trace_array *tr, int cpu) ftrace_enable_cpu(); } +void tracing_reset_online_cpus(struct trace_array *tr) +{ + int cpu; + + tr->time_start = ftrace_now(tr->cpu); + + for_each_online_cpu(cpu) + tracing_reset(tr, cpu); +} + #define SAVED_CMDLINES 128 static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; static unsigned map_cmdline_to_pid[SAVED_CMDLINES]; @@ -581,6 +705,91 @@ static void trace_init_cmdlines(void) cmdline_idx = 0; } +static int trace_stop_count; +static DEFINE_SPINLOCK(tracing_start_lock); + +/** + * ftrace_off_permanent - disable all ftrace code permanently + * + * This should only be called when a serious anomally has + * been detected. This will turn off the function tracing, + * ring buffers, and other tracing utilites. It takes no + * locks and can be called from any context. + */ +void ftrace_off_permanent(void) +{ + tracing_disabled = 1; + ftrace_stop(); + tracing_off_permanent(); +} + +/** + * tracing_start - quick start of the tracer + * + * If tracing is enabled but was stopped by tracing_stop, + * this will start the tracer back up. + */ +void tracing_start(void) +{ + struct ring_buffer *buffer; + unsigned long flags; + + if (tracing_disabled) + return; + + spin_lock_irqsave(&tracing_start_lock, flags); + if (--trace_stop_count) + goto out; + + if (trace_stop_count < 0) { + /* Someone screwed up their debugging */ + WARN_ON_ONCE(1); + trace_stop_count = 0; + goto out; + } + + + buffer = global_trace.buffer; + if (buffer) + ring_buffer_record_enable(buffer); + + buffer = max_tr.buffer; + if (buffer) + ring_buffer_record_enable(buffer); + + ftrace_start(); + out: + spin_unlock_irqrestore(&tracing_start_lock, flags); +} + +/** + * tracing_stop - quick stop of the tracer + * + * Light weight way to stop tracing. Use in conjunction with + * tracing_start. + */ +void tracing_stop(void) +{ + struct ring_buffer *buffer; + unsigned long flags; + + ftrace_stop(); + spin_lock_irqsave(&tracing_start_lock, flags); + if (trace_stop_count++) + goto out; + + buffer = global_trace.buffer; + if (buffer) + ring_buffer_record_disable(buffer); + + buffer = max_tr.buffer; + if (buffer) + ring_buffer_record_disable(buffer); + + out: + spin_unlock_irqrestore(&tracing_start_lock, flags); +} + void trace_stop_cmdline_recording(void); static void trace_save_cmdline(struct task_struct *tsk) @@ -618,7 +827,7 @@ static void trace_save_cmdline(struct task_struct *tsk) spin_unlock(&trace_cmdline_lock); } -static char *trace_find_cmdline(int pid) +char *trace_find_cmdline(int pid) { char *cmdline = "<...>"; unsigned map; @@ -655,6 +864,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; + entry->tgid = (tsk) ? tsk->tgid : 0; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -691,6 +901,56 @@ trace_function(struct trace_array *tr, struct trace_array_cpu *data, ring_buffer_unlock_commit(tr->buffer, event, irq_flags); } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static void __trace_graph_entry(struct trace_array *tr, + struct trace_array_cpu *data, + struct ftrace_graph_ent *trace, + unsigned long flags, + int pc) +{ + struct ring_buffer_event *event; + struct ftrace_graph_ent_entry *entry; + unsigned long irq_flags; + + if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) + return; + + event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_GRAPH_ENT; + entry->graph_ent = *trace; + ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags); +} + +static void __trace_graph_return(struct trace_array *tr, + struct trace_array_cpu *data, + struct ftrace_graph_ret *trace, + unsigned long flags, + int pc) +{ + struct ring_buffer_event *event; + struct ftrace_graph_ret_entry *entry; + unsigned long irq_flags; + + if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled)))) + return; + + event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_GRAPH_RET; + entry->ret = *trace; + ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags); +} +#endif + void ftrace(struct trace_array *tr, struct trace_array_cpu *data, unsigned long ip, unsigned long parent_ip, unsigned long flags, @@ -742,6 +1002,46 @@ void __trace_stack(struct trace_array *tr, ftrace_trace_stack(tr, data, flags, skip, preempt_count()); } +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags, int pc) +{ +#ifdef CONFIG_STACKTRACE + struct ring_buffer_event *event; + struct userstack_entry *entry; + struct stack_trace trace; + unsigned long irq_flags; + + if (!(trace_flags & TRACE_ITER_USERSTACKTRACE)) + return; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_USER_STACK; + + memset(&entry->caller, 0, sizeof(entry->caller)); + + trace.nr_entries = 0; + trace.max_entries = FTRACE_STACK_ENTRIES; + trace.skip = 0; + trace.entries = entry->caller; + + save_stack_trace_user(&trace); + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); +#endif +} + +void __trace_userstack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags) +{ + ftrace_trace_userstack(tr, data, flags, preempt_count()); +} + static void ftrace_trace_special(void *__tr, void *__data, unsigned long arg1, unsigned long arg2, unsigned long arg3, @@ -765,6 +1065,7 @@ ftrace_trace_special(void *__tr, void *__data, entry->arg3 = arg3; ring_buffer_unlock_commit(tr->buffer, event, irq_flags); ftrace_trace_stack(tr, data, irq_flags, 4, pc); + ftrace_trace_userstack(tr, data, irq_flags, pc); trace_wake_up(); } @@ -803,6 +1104,7 @@ tracing_sched_switch_trace(struct trace_array *tr, entry->next_cpu = task_cpu(next); ring_buffer_unlock_commit(tr->buffer, event, irq_flags); ftrace_trace_stack(tr, data, flags, 5, pc); + ftrace_trace_userstack(tr, data, flags, pc); } void @@ -832,6 +1134,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_cpu = task_cpu(wakee); ring_buffer_unlock_commit(tr->buffer, event, irq_flags); ftrace_trace_stack(tr, data, flags, 6, pc); + ftrace_trace_userstack(tr, data, flags, pc); trace_wake_up(); } @@ -841,26 +1144,28 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { struct trace_array *tr = &global_trace; struct trace_array_cpu *data; + unsigned long flags; int cpu; int pc; - if (tracing_disabled || !tr->ctrl) + if (tracing_disabled) return; pc = preempt_count(); - preempt_disable_notrace(); + local_irq_save(flags); cpu = raw_smp_processor_id(); data = tr->data[cpu]; - if (likely(!atomic_read(&data->disabled))) + if (likely(atomic_inc_return(&data->disabled) == 1)) ftrace_trace_special(tr, data, arg1, arg2, arg3, pc); - preempt_enable_notrace(); + atomic_dec(&data->disabled); + local_irq_restore(flags); } #ifdef CONFIG_FUNCTION_TRACER static void -function_trace_call(unsigned long ip, unsigned long parent_ip) +function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) { struct trace_array *tr = &global_trace; struct trace_array_cpu *data; @@ -873,8 +1178,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) return; pc = preempt_count(); - resched = need_resched(); - preempt_disable_notrace(); + resched = ftrace_preempt_disable(); local_save_flags(flags); cpu = raw_smp_processor_id(); data = tr->data[cpu]; @@ -884,11 +1188,96 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) trace_function(tr, data, ip, parent_ip, flags, pc); atomic_dec(&data->disabled); - if (resched) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); + ftrace_preempt_enable(resched); +} + +static void +function_trace_call(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = &global_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + if (unlikely(!ftrace_function_enabled)) + return; + + /* + * Need to use raw, since this must be called before the + * recursive protection is performed. + */ + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) { + pc = preempt_count(); + trace_function(tr, data, ip, parent_ip, flags, pc); + } + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +int trace_graph_entry(struct ftrace_graph_ent *trace) +{ + struct trace_array *tr = &global_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + if (!ftrace_trace_task(current)) + return 0; + + if (!ftrace_graph_addr(trace->func)) + return 0; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + if (likely(disabled == 1)) { + pc = preempt_count(); + __trace_graph_entry(tr, data, trace, flags, pc); + } + /* Only do the atomic if it is not already set */ + if (!test_tsk_trace_graph(current)) + set_tsk_trace_graph(current); + atomic_dec(&data->disabled); + local_irq_restore(flags); + + return 1; +} + +void trace_graph_return(struct ftrace_graph_ret *trace) +{ + struct trace_array *tr = &global_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + int pc; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + if (likely(disabled == 1)) { + pc = preempt_count(); + __trace_graph_return(tr, data, trace, flags, pc); + } + if (!trace->depth) + clear_tsk_trace_graph(current); + atomic_dec(&data->disabled); + local_irq_restore(flags); } +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ static struct ftrace_ops trace_ops __read_mostly = { @@ -898,9 +1287,14 @@ static struct ftrace_ops trace_ops __read_mostly = void tracing_start_function_trace(void) { ftrace_function_enabled = 0; + + if (trace_flags & TRACE_ITER_PREEMPTONLY) + trace_ops.func = function_trace_call_preempt_only; + else + trace_ops.func = function_trace_call; + register_ftrace_function(&trace_ops); - if (tracer_enabled) - ftrace_function_enabled = 1; + ftrace_function_enabled = 1; } void tracing_stop_function_trace(void) @@ -912,9 +1306,10 @@ void tracing_stop_function_trace(void) enum trace_file_type { TRACE_FILE_LAT_FMT = 1, + TRACE_FILE_ANNOTATE = 2, }; -static void trace_iterator_increment(struct trace_iterator *iter, int cpu) +static void trace_iterator_increment(struct trace_iterator *iter) { /* Don't allow ftrace to trace into the ring buffers */ ftrace_disable_cpu(); @@ -993,7 +1388,7 @@ static void *find_next_entry_inc(struct trace_iterator *iter) iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts); if (iter->ent) - trace_iterator_increment(iter, iter->cpu); + trace_iterator_increment(iter); return iter->ent ? iter : NULL; } @@ -1047,10 +1442,6 @@ static void *s_start(struct seq_file *m, loff_t *pos) atomic_inc(&trace_record_cmdline_disabled); - /* let the tracer grab locks here if needed */ - if (current_trace->start) - current_trace->start(iter); - if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; @@ -1077,14 +1468,7 @@ static void *s_start(struct seq_file *m, loff_t *pos) static void s_stop(struct seq_file *m, void *p) { - struct trace_iterator *iter = m->private; - atomic_dec(&trace_record_cmdline_disabled); - - /* let the tracer release locks here if needed */ - if (current_trace && current_trace == iter->trace && iter->trace->stop) - iter->trace->stop(iter); - mutex_unlock(&trace_types_lock); } @@ -1143,7 +1527,7 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt, # define IP_FMT "%016lx" #endif -static int +int seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) { int ret; @@ -1164,6 +1548,78 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) return ret; } +static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm, + unsigned long ip, unsigned long sym_flags) +{ + struct file *file = NULL; + unsigned long vmstart = 0; + int ret = 1; + + if (mm) { + const struct vm_area_struct *vma; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, ip); + if (vma) { + file = vma->vm_file; + vmstart = vma->vm_start; + } + if (file) { + ret = trace_seq_path(s, &file->f_path); + if (ret) + ret = trace_seq_printf(s, "[+0x%lx]", ip - vmstart); + } + up_read(&mm->mmap_sem); + } + if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file)) + ret = trace_seq_printf(s, " <" IP_FMT ">", ip); + return ret; +} + +static int +seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s, + unsigned long sym_flags) +{ + struct mm_struct *mm = NULL; + int ret = 1; + unsigned int i; + + if (trace_flags & TRACE_ITER_SYM_USEROBJ) { + struct task_struct *task; + /* + * we do the lookup on the thread group leader, + * since individual threads might have already quit! + */ + rcu_read_lock(); + task = find_task_by_vpid(entry->ent.tgid); + if (task) + mm = get_task_mm(task); + rcu_read_unlock(); + } + + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + unsigned long ip = entry->caller[i]; + + if (ip == ULONG_MAX || !ret) + break; + if (i && ret) + ret = trace_seq_puts(s, " <- "); + if (!ip) { + if (ret) + ret = trace_seq_puts(s, "??"); + continue; + } + if (!ret) + break; + if (ret) + ret = seq_print_user_ip(s, mm, ip, sym_flags); + } + + if (mm) + mmput(mm); + return ret; +} + static void print_lat_help_header(struct seq_file *m) { seq_puts(m, "# _------=> CPU# \n"); @@ -1301,6 +1757,13 @@ lat_print_timestamp(struct trace_seq *s, u64 abs_usecs, static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; +static int task_state_char(unsigned long state) +{ + int bit = state ? __ffs(state) + 1 : 0; + + return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; +} + /* * The message is supposed to contain an ending newline. * If the printing stops prematurely, try to add a newline of our own. @@ -1338,6 +1801,23 @@ void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter) trace_seq_putc(s, '\n'); } +static void test_cpu_buff_start(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + + if (!(trace_flags & TRACE_ITER_ANNOTATE)) + return; + + if (!(iter->iter_flags & TRACE_FILE_ANNOTATE)) + return; + + if (cpumask_test_cpu(iter->cpu, iter->started)) + return; + + cpumask_set_cpu(iter->cpu, iter->started); + trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu); +} + static enum print_line_t print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) { @@ -1352,11 +1832,12 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) char *comm; int S, T; int i; - unsigned state; if (entry->type == TRACE_CONT) return TRACE_TYPE_HANDLED; + test_cpu_buff_start(iter); + next_entry = find_next_entry(iter, NULL, &next_ts); if (!next_entry) next_ts = iter->ts; @@ -1396,12 +1877,8 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) trace_assign_type(field, entry); - T = field->next_state < sizeof(state_to_char) ? - state_to_char[field->next_state] : 'X'; - - state = field->prev_state ? - __ffs(field->prev_state) + 1 : 0; - S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X'; + T = task_state_char(field->next_state); + S = task_state_char(field->prev_state); comm = trace_find_cmdline(field->next_pid); trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", field->prev_pid, @@ -1448,6 +1925,27 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) trace_seq_print_cont(s, iter); break; } + case TRACE_BRANCH: { + struct trace_branch *field; + + trace_assign_type(field, entry); + + trace_seq_printf(s, "[%s] %s:%s:%d\n", + field->correct ? " ok " : " MISS ", + field->func, + field->file, + field->line); + break; + } + case TRACE_USER_STACK: { + struct userstack_entry *field; + + trace_assign_type(field, entry); + + seq_print_userip_objs(field, s, sym_flags); + trace_seq_putc(s, '\n'); + break; + } default: trace_seq_printf(s, "Unknown type %d\n", entry->type); } @@ -1472,6 +1970,8 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (entry->type == TRACE_CONT) return TRACE_TYPE_HANDLED; + test_cpu_buff_start(iter); + comm = trace_find_cmdline(iter->ent->pid); t = ns2usecs(iter->ts); @@ -1519,10 +2019,8 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) trace_assign_type(field, entry); - S = field->prev_state < sizeof(state_to_char) ? - state_to_char[field->prev_state] : 'X'; - T = field->next_state < sizeof(state_to_char) ? - state_to_char[field->next_state] : 'X'; + T = task_state_char(field->next_state); + S = task_state_char(field->prev_state); ret = trace_seq_printf(s, " %5d:%3d:%c %s [%03d] %5d:%3d:%c\n", field->prev_pid, field->prev_prio, @@ -1581,6 +2079,37 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) trace_seq_print_cont(s, iter); break; } + case TRACE_GRAPH_RET: { + return print_graph_function(iter); + } + case TRACE_GRAPH_ENT: { + return print_graph_function(iter); + } + case TRACE_BRANCH: { + struct trace_branch *field; + + trace_assign_type(field, entry); + + trace_seq_printf(s, "[%s] %s:%s:%d\n", + field->correct ? " ok " : " MISS ", + field->func, + field->file, + field->line); + break; + } + case TRACE_USER_STACK: { + struct userstack_entry *field; + + trace_assign_type(field, entry); + + ret = seq_print_userip_objs(field, s, sym_flags); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + ret = trace_seq_putc(s, '\n'); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + break; + } } return TRACE_TYPE_HANDLED; } @@ -1621,12 +2150,9 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter) trace_assign_type(field, entry); - S = field->prev_state < sizeof(state_to_char) ? - state_to_char[field->prev_state] : 'X'; - T = field->next_state < sizeof(state_to_char) ? - state_to_char[field->next_state] : 'X'; - if (entry->type == TRACE_WAKE) - S = '+'; + T = task_state_char(field->next_state); + S = entry->type == TRACE_WAKE ? '+' : + task_state_char(field->prev_state); ret = trace_seq_printf(s, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -1640,6 +2166,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter) break; } case TRACE_SPECIAL: + case TRACE_USER_STACK: case TRACE_STACK: { struct special_entry *field; @@ -1712,12 +2239,9 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter) trace_assign_type(field, entry); - S = field->prev_state < sizeof(state_to_char) ? - state_to_char[field->prev_state] : 'X'; - T = field->next_state < sizeof(state_to_char) ? - state_to_char[field->next_state] : 'X'; - if (entry->type == TRACE_WAKE) - S = '+'; + T = task_state_char(field->next_state); + S = entry->type == TRACE_WAKE ? '+' : + task_state_char(field->prev_state); SEQ_PUT_HEX_FIELD_RET(s, field->prev_pid); SEQ_PUT_HEX_FIELD_RET(s, field->prev_prio); SEQ_PUT_HEX_FIELD_RET(s, S); @@ -1728,6 +2252,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter) break; } case TRACE_SPECIAL: + case TRACE_USER_STACK: case TRACE_STACK: { struct special_entry *field; @@ -1744,6 +2269,25 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter) return TRACE_TYPE_HANDLED; } +static enum print_line_t print_printk_msg_only(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct print_entry *field; + int ret; + + trace_assign_type(field, entry); + + ret = trace_seq_printf(s, field->buf); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + if (entry->flags & TRACE_FLAG_CONT) + trace_seq_print_cont(s, iter); + + return TRACE_TYPE_HANDLED; +} + static enum print_line_t print_bin_fmt(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; @@ -1782,6 +2326,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter) break; } case TRACE_SPECIAL: + case TRACE_USER_STACK: case TRACE_STACK: { struct special_entry *field; @@ -1823,6 +2368,11 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter) return ret; } + if (iter->ent->type == TRACE_PRINT && + trace_flags & TRACE_ITER_PRINTK && + trace_flags & TRACE_ITER_PRINTK_MSGONLY) + return print_printk_msg_only(iter); + if (trace_flags & TRACE_ITER_BIN) return print_bin_fmt(iter); @@ -1847,7 +2397,9 @@ static int s_show(struct seq_file *m, void *v) seq_printf(m, "# tracer: %s\n", iter->trace->name); seq_puts(m, "#\n"); } - if (iter->iter_flags & TRACE_FILE_LAT_FMT) { + if (iter->trace && iter->trace->print_header) + iter->trace->print_header(m); + else if (iter->iter_flags & TRACE_FILE_LAT_FMT) { /* print nothing if the buffers are empty */ if (trace_empty(iter)) return 0; @@ -1899,6 +2451,15 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) iter->trace = current_trace; iter->pos = -1; + /* Notify the tracer early; before we stop tracing. */ + if (iter->trace && iter->trace->open) + iter->trace->open(iter); + + /* Annotate start of buffers if we had overruns */ + if (ring_buffer_overruns(iter->tr->buffer)) + iter->iter_flags |= TRACE_FILE_ANNOTATE; + + for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = @@ -1917,13 +2478,7 @@ __tracing_open(struct inode *inode, struct file *file, int *ret) m->private = iter; /* stop the trace while dumping */ - if (iter->tr->ctrl) { - tracer_enabled = 0; - ftrace_function_enabled = 0; - } - - if (iter->trace && iter->trace->open) - iter->trace->open(iter); + tracing_stop(); mutex_unlock(&trace_types_lock); @@ -1966,14 +2521,7 @@ int tracing_release(struct inode *inode, struct file *file) iter->trace->close(iter); /* reenable tracing if it was previously enabled */ - if (iter->tr->ctrl) { - tracer_enabled = 1; - /* - * It is safe to enable function tracing even if it - * isn't used - */ - ftrace_function_enabled = 1; - } + tracing_start(); mutex_unlock(&trace_types_lock); seq_release(inode, file); @@ -2098,13 +2646,7 @@ static struct file_operations show_traces_fops = { /* * Only trace on a CPU if the bitmask is set: */ -static cpumask_t tracing_cpumask = CPU_MASK_ALL; - -/* - * When tracing/tracing_cpu_mask is modified then this holds - * the new bitmask we are about to install: - */ -static cpumask_t tracing_cpumask_new; +static cpumask_var_t tracing_cpumask; /* * The tracer itself will not take this lock, but still we want @@ -2145,39 +2687,45 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) { int err, cpu; + cpumask_var_t tracing_cpumask_new; + + if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) + return -ENOMEM; mutex_lock(&tracing_cpumask_update_lock); err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); if (err) goto err_unlock; - raw_local_irq_disable(); + local_irq_disable(); __raw_spin_lock(&ftrace_max_lock); for_each_tracing_cpu(cpu) { /* * Increase/decrease the disabled counter if we are * about to flip a bit in the cpumask: */ - if (cpu_isset(cpu, tracing_cpumask) && - !cpu_isset(cpu, tracing_cpumask_new)) { + if (cpumask_test_cpu(cpu, tracing_cpumask) && + !cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_inc(&global_trace.data[cpu]->disabled); } - if (!cpu_isset(cpu, tracing_cpumask) && - cpu_isset(cpu, tracing_cpumask_new)) { + if (!cpumask_test_cpu(cpu, tracing_cpumask) && + cpumask_test_cpu(cpu, tracing_cpumask_new)) { atomic_dec(&global_trace.data[cpu]->disabled); } } __raw_spin_unlock(&ftrace_max_lock); - raw_local_irq_enable(); + local_irq_enable(); - tracing_cpumask = tracing_cpumask_new; + cpumask_copy(tracing_cpumask, tracing_cpumask_new); mutex_unlock(&tracing_cpumask_update_lock); + free_cpumask_var(tracing_cpumask_new); return count; err_unlock: mutex_unlock(&tracing_cpumask_update_lock); + free_cpumask_var(tracing_cpumask); return err; } @@ -2189,13 +2737,16 @@ static struct file_operations tracing_cpumask_fops = { }; static ssize_t -tracing_iter_ctrl_read(struct file *filp, char __user *ubuf, +tracing_trace_options_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { + int i; char *buf; int r = 0; int len = 0; - int i; + u32 tracer_flags = current_trace->flags->val; + struct tracer_opt *trace_opts = current_trace->flags->opts; + /* calulate max size */ for (i = 0; trace_options[i]; i++) { @@ -2203,6 +2754,15 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf, len += 3; /* "no" and space */ } + /* + * Increase the size with names of options specific + * of the current tracer. + */ + for (i = 0; trace_opts[i].name; i++) { + len += strlen(trace_opts[i].name); + len += 3; /* "no" and space */ + } + /* +2 for \n and \0 */ buf = kmalloc(len + 2, GFP_KERNEL); if (!buf) @@ -2215,6 +2775,15 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf, r += sprintf(buf + r, "no%s ", trace_options[i]); } + for (i = 0; trace_opts[i].name; i++) { + if (tracer_flags & trace_opts[i].bit) + r += sprintf(buf + r, "%s ", + trace_opts[i].name); + else + r += sprintf(buf + r, "no%s ", + trace_opts[i].name); + } + r += sprintf(buf + r, "\n"); WARN_ON(r >= len + 2); @@ -2225,13 +2794,48 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf, return r; } +/* Try to assign a tracer specific option */ +static int set_tracer_option(struct tracer *trace, char *cmp, int neg) +{ + struct tracer_flags *trace_flags = trace->flags; + struct tracer_opt *opts = NULL; + int ret = 0, i = 0; + int len; + + for (i = 0; trace_flags->opts[i].name; i++) { + opts = &trace_flags->opts[i]; + len = strlen(opts->name); + + if (strncmp(cmp, opts->name, len) == 0) { + ret = trace->set_flag(trace_flags->val, + opts->bit, !neg); + break; + } + } + /* Not found */ + if (!trace_flags->opts[i].name) + return -EINVAL; + + /* Refused to handle */ + if (ret) + return ret; + + if (neg) + trace_flags->val &= ~opts->bit; + else + trace_flags->val |= opts->bit; + + return 0; +} + static ssize_t -tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf, +tracing_trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[64]; char *cmp = buf; int neg = 0; + int ret; int i; if (cnt >= sizeof(buf)) @@ -2258,11 +2862,13 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf, break; } } - /* - * If no option could be set, return an error: - */ - if (!trace_options[i]) - return -EINVAL; + + /* If no option could be set, test the specific tracer options */ + if (!trace_options[i]) { + ret = set_tracer_option(current_trace, cmp, neg); + if (ret) + return ret; + } filp->f_pos += cnt; @@ -2271,8 +2877,8 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf, static struct file_operations tracing_iter_fops = { .open = tracing_open_generic, - .read = tracing_iter_ctrl_read, - .write = tracing_iter_ctrl_write, + .read = tracing_trace_options_read, + .write = tracing_trace_options_write, }; static const char readme_msg[] = @@ -2286,9 +2892,9 @@ static const char readme_msg[] = "# echo sched_switch > /debug/tracing/current_tracer\n" "# cat /debug/tracing/current_tracer\n" "sched_switch\n" - "# cat /debug/tracing/iter_ctrl\n" + "# cat /debug/tracing/trace_options\n" "noprint-parent nosym-offset nosym-addr noverbose\n" - "# echo print-parent > /debug/tracing/iter_ctrl\n" + "# echo print-parent > /debug/tracing/trace_options\n" "# echo 1 > /debug/tracing/tracing_enabled\n" "# cat /debug/tracing/trace > /tmp/trace.txt\n" "echo 0 > /debug/tracing/tracing_enabled\n" @@ -2311,11 +2917,10 @@ static ssize_t tracing_ctrl_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct trace_array *tr = filp->private_data; char buf[64]; int r; - r = sprintf(buf, "%ld\n", tr->ctrl); + r = sprintf(buf, "%u\n", tracer_enabled); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } @@ -2343,16 +2948,18 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf, val = !!val; mutex_lock(&trace_types_lock); - if (tr->ctrl ^ val) { - if (val) + if (tracer_enabled ^ val) { + if (val) { tracer_enabled = 1; - else + if (current_trace->start) + current_trace->start(tr); + tracing_start(); + } else { tracer_enabled = 0; - - tr->ctrl = val; - - if (current_trace && current_trace->ctrl_update) - current_trace->ctrl_update(tr); + tracing_stop(); + if (current_trace->stop) + current_trace->stop(tr); + } } mutex_unlock(&trace_types_lock); @@ -2378,29 +2985,11 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf, return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } -static ssize_t -tracing_set_trace_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +static int tracing_set_tracer(char *buf) { struct trace_array *tr = &global_trace; struct tracer *t; - char buf[max_tracer_type_len+1]; - int i; - size_t ret; - - ret = cnt; - - if (cnt > max_tracer_type_len) - cnt = max_tracer_type_len; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - - /* strip ending whitespace. */ - for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) - buf[i] = 0; + int ret = 0; mutex_lock(&trace_types_lock); for (t = trace_types; t; t = t->next) { @@ -2414,18 +3003,52 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, if (t == current_trace) goto out; + trace_branch_disable(); if (current_trace && current_trace->reset) current_trace->reset(tr); current_trace = t; - if (t->init) - t->init(tr); + if (t->init) { + ret = t->init(tr); + if (ret) + goto out; + } + trace_branch_enable(tr); out: mutex_unlock(&trace_types_lock); - if (ret > 0) - filp->f_pos += ret; + return ret; +} + +static ssize_t +tracing_set_trace_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[max_tracer_type_len+1]; + int i; + size_t ret; + int err; + + ret = cnt; + + if (cnt > max_tracer_type_len) + cnt = max_tracer_type_len; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + /* strip ending whitespace. */ + for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) + buf[i] = 0; + + err = tracing_set_tracer(buf); + if (err) + return err; + + filp->f_pos += ret; return ret; } @@ -2491,7 +3114,16 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) if (!iter) return -ENOMEM; + if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { + kfree(iter); + return -ENOMEM; + } + mutex_lock(&trace_types_lock); + + /* trace pipe does not show start of buffer */ + cpumask_setall(iter->started); + iter->tr = &global_trace; iter->trace = current_trace; filp->private_data = iter; @@ -2507,6 +3139,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file) { struct trace_iterator *iter = file->private_data; + free_cpumask_var(iter->started); kfree(iter); atomic_dec(&tracing_reader); @@ -2667,7 +3300,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, char buf[64]; int r; - r = sprintf(buf, "%lu\n", tr->entries); + r = sprintf(buf, "%lu\n", tr->entries >> 10); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } @@ -2678,7 +3311,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, unsigned long val; char buf[64]; int ret, cpu; - struct trace_array *tr = filp->private_data; if (cnt >= sizeof(buf)) return -EINVAL; @@ -2698,12 +3330,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, mutex_lock(&trace_types_lock); - if (tr->ctrl) { - cnt = -EBUSY; - pr_info("ftrace: please disable tracing" - " before modifying buffer size\n"); - goto out; - } + tracing_stop(); /* disable all cpu buffers */ for_each_tracing_cpu(cpu) { @@ -2713,6 +3340,9 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, atomic_inc(&max_tr.data[cpu]->disabled); } + /* value is in KB */ + val <<= 10; + if (val != global_trace.entries) { ret = ring_buffer_resize(global_trace.buffer, val); if (ret < 0) { @@ -2751,6 +3381,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, atomic_dec(&max_tr.data[cpu]->disabled); } + tracing_start(); max_tr.entries = global_trace.entries; mutex_unlock(&trace_types_lock); @@ -2762,7 +3393,7 @@ static int mark_printk(const char *fmt, ...) int ret; va_list args; va_start(args, fmt); - ret = trace_vprintk(0, fmt, args); + ret = trace_vprintk(0, -1, fmt, args); va_end(args); return ret; } @@ -2773,9 +3404,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, { char *buf; char *end; - struct trace_array *tr = &global_trace; - if (!tr->ctrl || tracing_disabled) + if (tracing_disabled) return -EINVAL; if (cnt > TRACE_BUF_SIZE) @@ -2841,22 +3471,38 @@ static struct file_operations tracing_mark_fops = { #ifdef CONFIG_DYNAMIC_FTRACE +int __weak ftrace_arch_read_dyn_info(char *buf, int size) +{ + return 0; +} + static ssize_t -tracing_read_long(struct file *filp, char __user *ubuf, +tracing_read_dyn_info(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { + static char ftrace_dyn_info_buffer[1024]; + static DEFINE_MUTEX(dyn_info_mutex); unsigned long *p = filp->private_data; - char buf[64]; + char *buf = ftrace_dyn_info_buffer; + int size = ARRAY_SIZE(ftrace_dyn_info_buffer); int r; - r = sprintf(buf, "%ld\n", *p); + mutex_lock(&dyn_info_mutex); + r = sprintf(buf, "%ld ", *p); - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + r += ftrace_arch_read_dyn_info(buf+r, (size-1)-r); + buf[r++] = '\n'; + + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + + mutex_unlock(&dyn_info_mutex); + + return r; } -static struct file_operations tracing_read_long_fops = { +static struct file_operations tracing_dyn_info_fops = { .open = tracing_open_generic, - .read = tracing_read_long, + .read = tracing_read_dyn_info, }; #endif @@ -2897,10 +3543,10 @@ static __init int tracer_init_debugfs(void) if (!entry) pr_warning("Could not create debugfs 'tracing_enabled' entry\n"); - entry = debugfs_create_file("iter_ctrl", 0644, d_tracer, + entry = debugfs_create_file("trace_options", 0644, d_tracer, NULL, &tracing_iter_fops); if (!entry) - pr_warning("Could not create debugfs 'iter_ctrl' entry\n"); + pr_warning("Could not create debugfs 'trace_options' entry\n"); entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer, NULL, &tracing_cpumask_fops); @@ -2950,11 +3596,11 @@ static __init int tracer_init_debugfs(void) pr_warning("Could not create debugfs " "'trace_pipe' entry\n"); - entry = debugfs_create_file("trace_entries", 0644, d_tracer, + entry = debugfs_create_file("buffer_size_kb", 0644, d_tracer, &global_trace, &tracing_entries_fops); if (!entry) pr_warning("Could not create debugfs " - "'trace_entries' entry\n"); + "'buffer_size_kb' entry\n"); entry = debugfs_create_file("trace_marker", 0220, d_tracer, NULL, &tracing_mark_fops); @@ -2965,7 +3611,7 @@ static __init int tracer_init_debugfs(void) #ifdef CONFIG_DYNAMIC_FTRACE entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer, &ftrace_update_tot_cnt, - &tracing_read_long_fops); + &tracing_dyn_info_fops); if (!entry) pr_warning("Could not create debugfs " "'dyn_ftrace_total_info' entry\n"); @@ -2976,7 +3622,7 @@ static __init int tracer_init_debugfs(void) return 0; } -int trace_vprintk(unsigned long ip, const char *fmt, va_list args) +int trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args) { static DEFINE_SPINLOCK(trace_buf_lock); static char trace_buf[TRACE_BUF_SIZE]; @@ -2984,11 +3630,11 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args) struct ring_buffer_event *event; struct trace_array *tr = &global_trace; struct trace_array_cpu *data; - struct print_entry *entry; - unsigned long flags, irq_flags; int cpu, len = 0, size, pc; + struct print_entry *entry; + unsigned long irq_flags; - if (!tr->ctrl || tracing_disabled) + if (tracing_disabled || tracing_selftest_running) return 0; pc = preempt_count(); @@ -2999,7 +3645,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args) if (unlikely(atomic_read(&data->disabled))) goto out; - spin_lock_irqsave(&trace_buf_lock, flags); + pause_graph_tracing(); + spin_lock_irqsave(&trace_buf_lock, irq_flags); len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args); len = min(len, TRACE_BUF_SIZE-1); @@ -3010,17 +3657,18 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args) if (!event) goto out_unlock; entry = ring_buffer_event_data(event); - tracing_generic_entry_update(&entry->ent, flags, pc); + tracing_generic_entry_update(&entry->ent, irq_flags, pc); entry->ent.type = TRACE_PRINT; entry->ip = ip; + entry->depth = depth; memcpy(&entry->buf, trace_buf, len); entry->buf[len] = 0; ring_buffer_unlock_commit(tr->buffer, event, irq_flags); out_unlock: - spin_unlock_irqrestore(&trace_buf_lock, flags); - + spin_unlock_irqrestore(&trace_buf_lock, irq_flags); + unpause_graph_tracing(); out: preempt_enable_notrace(); @@ -3037,7 +3685,7 @@ int __ftrace_printk(unsigned long ip, const char *fmt, ...) return 0; va_start(ap, fmt); - ret = trace_vprintk(ip, fmt, ap); + ret = trace_vprintk(ip, task_curr_ret_stack(current), fmt, ap); va_end(ap); return ret; } @@ -3046,7 +3694,8 @@ EXPORT_SYMBOL_GPL(__ftrace_printk); static int trace_panic_handler(struct notifier_block *this, unsigned long event, void *unused) { - ftrace_dump(); + if (ftrace_dump_on_oops) + ftrace_dump(); return NOTIFY_OK; } @@ -3062,7 +3711,8 @@ static int trace_die_handler(struct notifier_block *self, { switch (val) { case DIE_OOPS: - ftrace_dump(); + if (ftrace_dump_on_oops) + ftrace_dump(); break; default: break; @@ -3103,13 +3753,11 @@ trace_printk_seq(struct trace_seq *s) trace_seq_reset(s); } - void ftrace_dump(void) { static DEFINE_SPINLOCK(ftrace_dump_lock); /* use static because iter can be a bit big for the stack */ static struct trace_iterator iter; - static cpumask_t mask; static int dump_ran; unsigned long flags; int cnt = 0, cpu; @@ -3128,6 +3776,9 @@ void ftrace_dump(void) atomic_inc(&global_trace.data[cpu]->disabled); } + /* don't look at user memory in panic mode */ + trace_flags &= ~TRACE_ITER_SYM_USEROBJ; + printk(KERN_TRACE "Dumping ftrace buffer:\n"); iter.tr = &global_trace; @@ -3140,8 +3791,6 @@ void ftrace_dump(void) * and then release the locks again. */ - cpus_clear(mask); - while (!trace_empty(&iter)) { if (!cnt) @@ -3177,19 +3826,28 @@ __init static int tracer_alloc_buffers(void) { struct trace_array_cpu *data; int i; + int ret = -ENOMEM; - /* TODO: make the number of buffers hot pluggable with CPUS */ - tracing_buffer_mask = cpu_possible_map; + if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL)) + goto out; + + if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL)) + goto out_free_buffer_mask; + + cpumask_copy(tracing_buffer_mask, cpu_possible_mask); + cpumask_copy(tracing_cpumask, cpu_all_mask); + /* TODO: make the number of buffers hot pluggable with CPUS */ global_trace.buffer = ring_buffer_alloc(trace_buf_size, TRACE_BUFFER_FLAGS); if (!global_trace.buffer) { printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); WARN_ON(1); - return 0; + goto out_free_cpumask; } global_trace.entries = ring_buffer_size(global_trace.buffer); + #ifdef CONFIG_TRACER_MAX_TRACE max_tr.buffer = ring_buffer_alloc(trace_buf_size, TRACE_BUFFER_FLAGS); @@ -3197,7 +3855,7 @@ __init static int tracer_alloc_buffers(void) printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n"); WARN_ON(1); ring_buffer_free(global_trace.buffer); - return 0; + goto out_free_cpumask; } max_tr.entries = ring_buffer_size(max_tr.buffer); WARN_ON(max_tr.entries != global_trace.entries); @@ -3221,15 +3879,20 @@ __init static int tracer_alloc_buffers(void) #endif /* All seems OK, enable tracing */ - global_trace.ctrl = tracer_enabled; tracing_disabled = 0; atomic_notifier_chain_register(&panic_notifier_list, &trace_panic_notifier); register_die_notifier(&trace_die_notifier); + ret = 0; - return 0; +out_free_cpumask: + free_cpumask_var(tracing_cpumask); +out_free_buffer_mask: + free_cpumask_var(tracing_buffer_mask); +out: + return ret; } early_initcall(tracer_alloc_buffers); fs_initcall(tracer_init_debugfs); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8465ad0..4d3d381 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -8,6 +8,7 @@ #include <linux/ring_buffer.h> #include <linux/mmiotrace.h> #include <linux/ftrace.h> +#include <trace/boot.h> enum trace_type { __TRACE_FIRST_TYPE = 0, @@ -21,7 +22,14 @@ enum trace_type { TRACE_SPECIAL, TRACE_MMIO_RW, TRACE_MMIO_MAP, - TRACE_BOOT, + TRACE_BRANCH, + TRACE_BOOT_CALL, + TRACE_BOOT_RET, + TRACE_GRAPH_RET, + TRACE_GRAPH_ENT, + TRACE_USER_STACK, + TRACE_HW_BRANCHES, + TRACE_POWER, __TRACE_LAST_TYPE }; @@ -38,6 +46,7 @@ struct trace_entry { unsigned char flags; unsigned char preempt_count; int pid; + int tgid; }; /* @@ -48,6 +57,18 @@ struct ftrace_entry { unsigned long ip; unsigned long parent_ip; }; + +/* Function call entry */ +struct ftrace_graph_ent_entry { + struct trace_entry ent; + struct ftrace_graph_ent graph_ent; +}; + +/* Function return entry */ +struct ftrace_graph_ret_entry { + struct trace_entry ent; + struct ftrace_graph_ret ret; +}; extern struct tracer boot_tracer; /* @@ -85,12 +106,18 @@ struct stack_entry { unsigned long caller[FTRACE_STACK_ENTRIES]; }; +struct userstack_entry { + struct trace_entry ent; + unsigned long caller[FTRACE_STACK_ENTRIES]; +}; + /* * ftrace_printk entry: */ struct print_entry { struct trace_entry ent; unsigned long ip; + int depth; char buf[]; }; @@ -112,9 +139,35 @@ struct trace_mmiotrace_map { struct mmiotrace_map map; }; -struct trace_boot { +struct trace_boot_call { struct trace_entry ent; - struct boot_trace initcall; + struct boot_trace_call boot_call; +}; + +struct trace_boot_ret { + struct trace_entry ent; + struct boot_trace_ret boot_ret; +}; + +#define TRACE_FUNC_SIZE 30 +#define TRACE_FILE_SIZE 20 +struct trace_branch { + struct trace_entry ent; + unsigned line; + char func[TRACE_FUNC_SIZE+1]; + char file[TRACE_FILE_SIZE+1]; + char correct; +}; + +struct hw_branch_entry { + struct trace_entry ent; + u64 from; + u64 to; +}; + +struct trace_power { + struct trace_entry ent; + struct power_trace state_data; }; /* @@ -172,7 +225,6 @@ struct trace_iterator; struct trace_array { struct ring_buffer *buffer; unsigned long entries; - long ctrl; int cpu; cycle_t time_start; struct task_struct *waiter; @@ -212,13 +264,22 @@ extern void __ftrace_bad_type(void); IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \ IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \ IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \ + IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\ IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \ IF_ASSIGN(var, ent, struct special_entry, 0); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \ TRACE_MMIO_RW); \ IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \ TRACE_MMIO_MAP); \ - IF_ASSIGN(var, ent, struct trace_boot, TRACE_BOOT); \ + IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\ + IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\ + IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \ + IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \ + TRACE_GRAPH_ENT); \ + IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \ + TRACE_GRAPH_RET); \ + IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\ + IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \ __ftrace_bad_type(); \ } while (0) @@ -229,29 +290,56 @@ enum print_line_t { TRACE_TYPE_UNHANDLED = 2 /* Relay to other output functions */ }; + +/* + * An option specific to a tracer. This is a boolean value. + * The bit is the bit index that sets its value on the + * flags value in struct tracer_flags. + */ +struct tracer_opt { + const char *name; /* Will appear on the trace_options file */ + u32 bit; /* Mask assigned in val field in tracer_flags */ +}; + +/* + * The set of specific options for a tracer. Your tracer + * have to set the initial value of the flags val. + */ +struct tracer_flags { + u32 val; + struct tracer_opt *opts; +}; + +/* Makes more easy to define a tracer opt */ +#define TRACER_OPT(s, b) .name = #s, .bit = b + /* * A specific tracer, represented by methods that operate on a trace array: */ struct tracer { const char *name; - void (*init)(struct trace_array *tr); + /* Your tracer should raise a warning if init fails */ + int (*init)(struct trace_array *tr); void (*reset)(struct trace_array *tr); + void (*start)(struct trace_array *tr); + void (*stop)(struct trace_array *tr); void (*open)(struct trace_iterator *iter); void (*pipe_open)(struct trace_iterator *iter); void (*close)(struct trace_iterator *iter); - void (*start)(struct trace_iterator *iter); - void (*stop)(struct trace_iterator *iter); ssize_t (*read)(struct trace_iterator *iter, struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos); - void (*ctrl_update)(struct trace_array *tr); #ifdef CONFIG_FTRACE_STARTUP_TEST int (*selftest)(struct tracer *trace, struct trace_array *tr); #endif + void (*print_header)(struct seq_file *m); enum print_line_t (*print_line)(struct trace_iterator *iter); + /* If you handled the flag setting, return 0 */ + int (*set_flag)(u32 old_flags, u32 bit, int set); struct tracer *next; int print_max; + struct tracer_flags *flags; }; struct trace_seq { @@ -279,10 +367,14 @@ struct trace_iterator { unsigned long iter_flags; loff_t pos; long idx; + + cpumask_var_t started; }; +int tracing_is_enabled(void); void trace_wake_up(void); void tracing_reset(struct trace_array *tr, int cpu); +void tracing_reset_online_cpus(struct trace_array *tr); int tracing_open_generic(struct inode *inode, struct file *filp); struct dentry *tracing_init_dentry(void); void init_tracer_sysprof_debugfs(struct dentry *d_tracer); @@ -321,8 +413,15 @@ void trace_function(struct trace_array *tr, unsigned long parent_ip, unsigned long flags, int pc); +void trace_graph_return(struct ftrace_graph_ret *trace); +int trace_graph_entry(struct ftrace_graph_ent *trace); +void trace_hw_branch(struct trace_array *tr, u64 from, u64 to); + void tracing_start_cmdline_record(void); void tracing_stop_cmdline_record(void); +void tracing_sched_switch_assign_trace(struct trace_array *tr); +void tracing_stop_sched_switch_record(void); +void tracing_start_sched_switch_record(void); int register_tracer(struct tracer *type); void unregister_tracer(struct tracer *type); @@ -358,6 +457,7 @@ struct tracer_switch_ops { struct tracer_switch_ops *next; }; +char *trace_find_cmdline(int pid); #endif /* CONFIG_CONTEXT_SWITCH_TRACER */ #ifdef CONFIG_DYNAMIC_FTRACE @@ -383,19 +483,79 @@ extern int trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr); +extern int trace_selftest_startup_branch(struct tracer *trace, + struct trace_array *tr); #endif /* CONFIG_FTRACE_STARTUP_TEST */ extern void *head_page(struct trace_array_cpu *data); extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...); extern void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter); + +extern int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, + unsigned long sym_flags); extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt); extern long ns2usecs(cycle_t nsec); -extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args); +extern int +trace_vprintk(unsigned long ip, int depth, const char *fmt, va_list args); extern unsigned long trace_flags; +/* Standard output formatting function used for function return traces */ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +extern enum print_line_t print_graph_function(struct trace_iterator *iter); + +#ifdef CONFIG_DYNAMIC_FTRACE +/* TODO: make this variable */ +#define FTRACE_GRAPH_MAX_FUNCS 32 +extern int ftrace_graph_count; +extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS]; + +static inline int ftrace_graph_addr(unsigned long addr) +{ + int i; + + if (!ftrace_graph_count || test_tsk_trace_graph(current)) + return 1; + + for (i = 0; i < ftrace_graph_count; i++) { + if (addr == ftrace_graph_funcs[i]) + return 1; + } + + return 0; +} +#else +static inline int ftrace_trace_addr(unsigned long addr) +{ + return 1; +} +static inline int ftrace_graph_addr(unsigned long addr) +{ + return 1; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#else /* CONFIG_FUNCTION_GRAPH_TRACER */ +static inline enum print_line_t +print_graph_function(struct trace_iterator *iter) +{ + return TRACE_TYPE_UNHANDLED; +} +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +extern struct pid *ftrace_pid_trace; + +static inline int ftrace_trace_task(struct task_struct *task) +{ + if (!ftrace_pid_trace) + return 1; + + return test_tsk_trace_trace(task); +} + /* * trace_iterator_flags is an enumeration that defines bit * positions into trace_flags that controls the output. @@ -415,8 +575,93 @@ enum trace_iterator_flags { TRACE_ITER_STACKTRACE = 0x100, TRACE_ITER_SCHED_TREE = 0x200, TRACE_ITER_PRINTK = 0x400, + TRACE_ITER_PREEMPTONLY = 0x800, + TRACE_ITER_BRANCH = 0x1000, + TRACE_ITER_ANNOTATE = 0x2000, + TRACE_ITER_USERSTACKTRACE = 0x4000, + TRACE_ITER_SYM_USEROBJ = 0x8000, + TRACE_ITER_PRINTK_MSGONLY = 0x10000 }; +/* + * TRACE_ITER_SYM_MASK masks the options in trace_flags that + * control the output of kernel symbols. + */ +#define TRACE_ITER_SYM_MASK \ + (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR) + extern struct tracer nop_trace; +/** + * ftrace_preempt_disable - disable preemption scheduler safe + * + * When tracing can happen inside the scheduler, there exists + * cases that the tracing might happen before the need_resched + * flag is checked. If this happens and the tracer calls + * preempt_enable (after a disable), a schedule might take place + * causing an infinite recursion. + * + * To prevent this, we read the need_recshed flag before + * disabling preemption. When we want to enable preemption we + * check the flag, if it is set, then we call preempt_enable_no_resched. + * Otherwise, we call preempt_enable. + * + * The rational for doing the above is that if need resched is set + * and we have yet to reschedule, we are either in an atomic location + * (where we do not need to check for scheduling) or we are inside + * the scheduler and do not want to resched. + */ +static inline int ftrace_preempt_disable(void) +{ + int resched; + + resched = need_resched(); + preempt_disable_notrace(); + + return resched; +} + +/** + * ftrace_preempt_enable - enable preemption scheduler safe + * @resched: the return value from ftrace_preempt_disable + * + * This is a scheduler safe way to enable preemption and not miss + * any preemption checks. The disabled saved the state of preemption. + * If resched is set, then we were either inside an atomic or + * are inside the scheduler (we would have already scheduled + * otherwise). In this case, we do not want to call normal + * preempt_enable, but preempt_enable_no_resched instead. + */ +static inline void ftrace_preempt_enable(int resched) +{ + if (resched) + preempt_enable_no_resched_notrace(); + else + preempt_enable_notrace(); +} + +#ifdef CONFIG_BRANCH_TRACER +extern int enable_branch_tracing(struct trace_array *tr); +extern void disable_branch_tracing(void); +static inline int trace_branch_enable(struct trace_array *tr) +{ + if (trace_flags & TRACE_ITER_BRANCH) + return enable_branch_tracing(tr); + return 0; +} +static inline void trace_branch_disable(void) +{ + /* due to races, always disable */ + disable_branch_tracing(); +} +#else +static inline int trace_branch_enable(struct trace_array *tr) +{ + return 0; +} +static inline void trace_branch_disable(void) +{ +} +#endif /* CONFIG_BRANCH_TRACER */ + #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index d0a5e50..366c8c3 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -13,101 +13,161 @@ #include "trace.h" static struct trace_array *boot_trace; -static int trace_boot_enabled; +static bool pre_initcalls_finished; - -/* Should be started after do_pre_smp_initcalls() in init/main.c */ +/* Tells the boot tracer that the pre_smp_initcalls are finished. + * So we are ready . + * It doesn't enable sched events tracing however. + * You have to call enable_boot_trace to do so. + */ void start_boot_trace(void) { - trace_boot_enabled = 1; + pre_initcalls_finished = true; } -void stop_boot_trace(void) +void enable_boot_trace(void) { - trace_boot_enabled = 0; + if (pre_initcalls_finished) + tracing_start_sched_switch_record(); } -void reset_boot_trace(struct trace_array *tr) +void disable_boot_trace(void) { - stop_boot_trace(); + if (pre_initcalls_finished) + tracing_stop_sched_switch_record(); } -static void boot_trace_init(struct trace_array *tr) +static int boot_trace_init(struct trace_array *tr) { int cpu; boot_trace = tr; - trace_boot_enabled = 0; - - for_each_cpu_mask(cpu, cpu_possible_map) + for_each_cpu(cpu, cpu_possible_mask) tracing_reset(tr, cpu); + + tracing_sched_switch_assign_trace(tr); + return 0; } -static void boot_trace_ctrl_update(struct trace_array *tr) +static enum print_line_t +initcall_call_print_line(struct trace_iterator *iter) { - if (tr->ctrl) - start_boot_trace(); + struct trace_entry *entry = iter->ent; + struct trace_seq *s = &iter->seq; + struct trace_boot_call *field; + struct boot_trace_call *call; + u64 ts; + unsigned long nsec_rem; + int ret; + + trace_assign_type(field, entry); + call = &field->boot_call; + ts = iter->ts; + nsec_rem = do_div(ts, 1000000000); + + ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n", + (unsigned long)ts, nsec_rem, call->func, call->caller); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; else - stop_boot_trace(); + return TRACE_TYPE_HANDLED; } -static enum print_line_t initcall_print_line(struct trace_iterator *iter) +static enum print_line_t +initcall_ret_print_line(struct trace_iterator *iter) { - int ret; struct trace_entry *entry = iter->ent; - struct trace_boot *field = (struct trace_boot *)entry; - struct boot_trace *it = &field->initcall; struct trace_seq *s = &iter->seq; - struct timespec calltime = ktime_to_timespec(it->calltime); - struct timespec rettime = ktime_to_timespec(it->rettime); - - if (entry->type == TRACE_BOOT) { - ret = trace_seq_printf(s, "[%5ld.%09ld] calling %s @ %i\n", - calltime.tv_sec, - calltime.tv_nsec, - it->func, it->caller); - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s " - "returned %d after %lld msecs\n", - rettime.tv_sec, - rettime.tv_nsec, - it->func, it->result, it->duration); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; + struct trace_boot_ret *field; + struct boot_trace_ret *init_ret; + u64 ts; + unsigned long nsec_rem; + int ret; + + trace_assign_type(field, entry); + init_ret = &field->boot_ret; + ts = iter->ts; + nsec_rem = do_div(ts, 1000000000); + + ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s " + "returned %d after %llu msecs\n", + (unsigned long) ts, + nsec_rem, + init_ret->func, init_ret->result, init_ret->duration); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + else return TRACE_TYPE_HANDLED; +} + +static enum print_line_t initcall_print_line(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + + switch (entry->type) { + case TRACE_BOOT_CALL: + return initcall_call_print_line(iter); + case TRACE_BOOT_RET: + return initcall_ret_print_line(iter); + default: + return TRACE_TYPE_UNHANDLED; } - return TRACE_TYPE_UNHANDLED; } struct tracer boot_tracer __read_mostly = { .name = "initcall", .init = boot_trace_init, - .reset = reset_boot_trace, - .ctrl_update = boot_trace_ctrl_update, + .reset = tracing_reset_online_cpus, .print_line = initcall_print_line, }; -void trace_boot(struct boot_trace *it, initcall_t fn) +void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { struct ring_buffer_event *event; - struct trace_boot *entry; - struct trace_array_cpu *data; + struct trace_boot_call *entry; unsigned long irq_flags; struct trace_array *tr = boot_trace; - if (!trace_boot_enabled) + if (!pre_initcalls_finished) return; /* Get its name now since this function could * disappear because it is in the .init section. */ - sprint_symbol(it->func, (unsigned long)fn); + sprint_symbol(bt->func, (unsigned long)fn); + preempt_disable(); + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, 0, 0); + entry->ent.type = TRACE_BOOT_CALL; + entry->boot_call = *bt; + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + + trace_wake_up(); + + out: + preempt_enable(); +} + +void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) +{ + struct ring_buffer_event *event; + struct trace_boot_ret *entry; + unsigned long irq_flags; + struct trace_array *tr = boot_trace; + + if (!pre_initcalls_finished) + return; + + sprint_symbol(bt->func, (unsigned long)fn); preempt_disable(); - data = tr->data[smp_processor_id()]; event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq_flags); @@ -115,8 +175,8 @@ void trace_boot(struct boot_trace *it, initcall_t fn) goto out; entry = ring_buffer_event_data(event); tracing_generic_entry_update(&entry->ent, 0, 0); - entry->ent.type = TRACE_BOOT; - entry->initcall = *it; + entry->ent.type = TRACE_BOOT_RET; + entry->boot_ret = *bt; ring_buffer_unlock_commit(tr->buffer, event, irq_flags); trace_wake_up(); diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c new file mode 100644 index 0000000..6c00feb --- /dev/null +++ b/kernel/trace/trace_branch.c @@ -0,0 +1,342 @@ +/* + * unlikely profiler + * + * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> + */ +#include <linux/kallsyms.h> +#include <linux/seq_file.h> +#include <linux/spinlock.h> +#include <linux/irqflags.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/ftrace.h> +#include <linux/hash.h> +#include <linux/fs.h> +#include <asm/local.h> +#include "trace.h" + +#ifdef CONFIG_BRANCH_TRACER + +static int branch_tracing_enabled __read_mostly; +static DEFINE_MUTEX(branch_tracing_mutex); +static struct trace_array *branch_tracer; + +static void +probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) +{ + struct trace_array *tr = branch_tracer; + struct ring_buffer_event *event; + struct trace_branch *entry; + unsigned long flags, irq_flags; + int cpu, pc; + const char *p; + + /* + * I would love to save just the ftrace_likely_data pointer, but + * this code can also be used by modules. Ugly things can happen + * if the module is unloaded, and then we go and read the + * pointer. This is slower, but much safer. + */ + + if (unlikely(!tr)) + return; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + if (atomic_inc_return(&tr->data[cpu]->disabled) != 1) + goto out; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + goto out; + + pc = preempt_count(); + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, flags, pc); + entry->ent.type = TRACE_BRANCH; + + /* Strip off the path, only save the file */ + p = f->file + strlen(f->file); + while (p >= f->file && *p != '/') + p--; + p++; + + strncpy(entry->func, f->func, TRACE_FUNC_SIZE); + strncpy(entry->file, p, TRACE_FILE_SIZE); + entry->func[TRACE_FUNC_SIZE] = 0; + entry->file[TRACE_FILE_SIZE] = 0; + entry->line = f->line; + entry->correct = val == expect; + + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + + out: + atomic_dec(&tr->data[cpu]->disabled); + local_irq_restore(flags); +} + +static inline +void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect) +{ + if (!branch_tracing_enabled) + return; + + probe_likely_condition(f, val, expect); +} + +int enable_branch_tracing(struct trace_array *tr) +{ + int ret = 0; + + mutex_lock(&branch_tracing_mutex); + branch_tracer = tr; + /* + * Must be seen before enabling. The reader is a condition + * where we do not need a matching rmb() + */ + smp_wmb(); + branch_tracing_enabled++; + mutex_unlock(&branch_tracing_mutex); + + return ret; +} + +void disable_branch_tracing(void) +{ + mutex_lock(&branch_tracing_mutex); + + if (!branch_tracing_enabled) + goto out_unlock; + + branch_tracing_enabled--; + + out_unlock: + mutex_unlock(&branch_tracing_mutex); +} + +static void start_branch_trace(struct trace_array *tr) +{ + enable_branch_tracing(tr); +} + +static void stop_branch_trace(struct trace_array *tr) +{ + disable_branch_tracing(); +} + +static int branch_trace_init(struct trace_array *tr) +{ + int cpu; + + for_each_online_cpu(cpu) + tracing_reset(tr, cpu); + + start_branch_trace(tr); + return 0; +} + +static void branch_trace_reset(struct trace_array *tr) +{ + stop_branch_trace(tr); +} + +struct tracer branch_trace __read_mostly = +{ + .name = "branch", + .init = branch_trace_init, + .reset = branch_trace_reset, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_branch, +#endif +}; + +__init static int init_branch_trace(void) +{ + return register_tracer(&branch_trace); +} + +device_initcall(init_branch_trace); +#else +static inline +void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect) +{ +} +#endif /* CONFIG_BRANCH_TRACER */ + +void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect) +{ + /* + * I would love to have a trace point here instead, but the + * trace point code is so inundated with unlikely and likely + * conditions that the recursive nightmare that exists is too + * much to try to get working. At least for now. + */ + trace_likely_condition(f, val, expect); + + /* FIXME: Make this atomic! */ + if (val == expect) + f->correct++; + else + f->incorrect++; +} +EXPORT_SYMBOL(ftrace_likely_update); + +struct ftrace_pointer { + void *start; + void *stop; + int hit; +}; + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + const struct ftrace_pointer *f = m->private; + struct ftrace_branch_data *p = v; + + (*pos)++; + + if (v == (void *)1) + return f->start; + + ++p; + + if ((void *)p >= (void *)f->stop) + return NULL; + + return p; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + void *t = (void *)1; + loff_t l = 0; + + for (; t && l < *pos; t = t_next(m, t, &l)) + ; + + return t; +} + +static void t_stop(struct seq_file *m, void *p) +{ +} + +static int t_show(struct seq_file *m, void *v) +{ + const struct ftrace_pointer *fp = m->private; + struct ftrace_branch_data *p = v; + const char *f; + long percent; + + if (v == (void *)1) { + if (fp->hit) + seq_printf(m, " miss hit %% "); + else + seq_printf(m, " correct incorrect %% "); + seq_printf(m, " Function " + " File Line\n" + " ------- --------- - " + " -------- " + " ---- ----\n"); + return 0; + } + + /* Only print the file, not the path */ + f = p->file + strlen(p->file); + while (f >= p->file && *f != '/') + f--; + f++; + + /* + * The miss is overlayed on correct, and hit on incorrect. + */ + if (p->correct) { + percent = p->incorrect * 100; + percent /= p->correct + p->incorrect; + } else + percent = p->incorrect ? 100 : -1; + + seq_printf(m, "%8lu %8lu ", p->correct, p->incorrect); + if (percent < 0) + seq_printf(m, " X "); + else + seq_printf(m, "%3ld ", percent); + seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line); + return 0; +} + +static struct seq_operations tracing_likely_seq_ops = { + .start = t_start, + .next = t_next, + .stop = t_stop, + .show = t_show, +}; + +static int tracing_branch_open(struct inode *inode, struct file *file) +{ + int ret; + + ret = seq_open(file, &tracing_likely_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = (void *)inode->i_private; + } + + return ret; +} + +static const struct file_operations tracing_branch_fops = { + .open = tracing_branch_open, + .read = seq_read, + .llseek = seq_lseek, +}; + +#ifdef CONFIG_PROFILE_ALL_BRANCHES +extern unsigned long __start_branch_profile[]; +extern unsigned long __stop_branch_profile[]; + +static const struct ftrace_pointer ftrace_branch_pos = { + .start = __start_branch_profile, + .stop = __stop_branch_profile, + .hit = 1, +}; + +#endif /* CONFIG_PROFILE_ALL_BRANCHES */ + +extern unsigned long __start_annotated_branch_profile[]; +extern unsigned long __stop_annotated_branch_profile[]; + +static const struct ftrace_pointer ftrace_annotated_branch_pos = { + .start = __start_annotated_branch_profile, + .stop = __stop_annotated_branch_profile, +}; + +static __init int ftrace_branch_init(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + + entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer, + (void *)&ftrace_annotated_branch_pos, + &tracing_branch_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'profile_annotatet_branch' entry\n"); + +#ifdef CONFIG_PROFILE_ALL_BRANCHES + entry = debugfs_create_file("profile_branch", 0444, d_tracer, + (void *)&ftrace_branch_pos, + &tracing_branch_fops); + if (!entry) + pr_warning("Could not create debugfs" + " 'profile_branch' entry\n"); +#endif + + return 0; +} + +device_initcall(ftrace_branch_init); diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 0f85a64..9236d7e 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -16,20 +16,10 @@ #include "trace.h" -static void function_reset(struct trace_array *tr) -{ - int cpu; - - tr->time_start = ftrace_now(tr->cpu); - - for_each_online_cpu(cpu) - tracing_reset(tr, cpu); -} - static void start_function_trace(struct trace_array *tr) { tr->cpu = get_cpu(); - function_reset(tr); + tracing_reset_online_cpus(tr); put_cpu(); tracing_start_cmdline_record(); @@ -42,24 +32,20 @@ static void stop_function_trace(struct trace_array *tr) tracing_stop_cmdline_record(); } -static void function_trace_init(struct trace_array *tr) +static int function_trace_init(struct trace_array *tr) { - if (tr->ctrl) - start_function_trace(tr); + start_function_trace(tr); + return 0; } static void function_trace_reset(struct trace_array *tr) { - if (tr->ctrl) - stop_function_trace(tr); + stop_function_trace(tr); } -static void function_trace_ctrl_update(struct trace_array *tr) +static void function_trace_start(struct trace_array *tr) { - if (tr->ctrl) - start_function_trace(tr); - else - stop_function_trace(tr); + tracing_reset_online_cpus(tr); } static struct tracer function_trace __read_mostly = @@ -67,7 +53,7 @@ static struct tracer function_trace __read_mostly = .name = "function", .init = function_trace_init, .reset = function_trace_reset, - .ctrl_update = function_trace_ctrl_update, + .start = function_trace_start, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_function, #endif diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c new file mode 100644 index 0000000..930c08e --- /dev/null +++ b/kernel/trace/trace_functions_graph.c @@ -0,0 +1,669 @@ +/* + * + * Function graph tracer. + * Copyright (c) 2008 Frederic Weisbecker <fweisbec@gmail.com> + * Mostly borrowed from function tracer which + * is Copyright (c) Steven Rostedt <srostedt@redhat.com> + * + */ +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/fs.h> + +#include "trace.h" + +#define TRACE_GRAPH_INDENT 2 + +/* Flag options */ +#define TRACE_GRAPH_PRINT_OVERRUN 0x1 +#define TRACE_GRAPH_PRINT_CPU 0x2 +#define TRACE_GRAPH_PRINT_OVERHEAD 0x4 +#define TRACE_GRAPH_PRINT_PROC 0x8 + +static struct tracer_opt trace_opts[] = { + /* Display overruns ? */ + { TRACER_OPT(funcgraph-overrun, TRACE_GRAPH_PRINT_OVERRUN) }, + /* Display CPU ? */ + { TRACER_OPT(funcgraph-cpu, TRACE_GRAPH_PRINT_CPU) }, + /* Display Overhead ? */ + { TRACER_OPT(funcgraph-overhead, TRACE_GRAPH_PRINT_OVERHEAD) }, + /* Display proc name/pid */ + { TRACER_OPT(funcgraph-proc, TRACE_GRAPH_PRINT_PROC) }, + { } /* Empty entry */ +}; + +static struct tracer_flags tracer_flags = { + /* Don't display overruns and proc by default */ + .val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD, + .opts = trace_opts +}; + +/* pid on the last trace processed */ +static pid_t last_pid[NR_CPUS] = { [0 ... NR_CPUS-1] = -1 }; + +static int graph_trace_init(struct trace_array *tr) +{ + int cpu, ret; + + for_each_online_cpu(cpu) + tracing_reset(tr, cpu); + + ret = register_ftrace_graph(&trace_graph_return, + &trace_graph_entry); + if (ret) + return ret; + tracing_start_cmdline_record(); + + return 0; +} + +static void graph_trace_reset(struct trace_array *tr) +{ + tracing_stop_cmdline_record(); + unregister_ftrace_graph(); +} + +static inline int log10_cpu(int nb) +{ + if (nb / 100) + return 3; + if (nb / 10) + return 2; + return 1; +} + +static enum print_line_t +print_graph_cpu(struct trace_seq *s, int cpu) +{ + int i; + int ret; + int log10_this = log10_cpu(cpu); + int log10_all = log10_cpu(cpumask_weight(cpu_online_mask)); + + + /* + * Start with a space character - to make it stand out + * to the right a bit when trace output is pasted into + * email: + */ + ret = trace_seq_printf(s, " "); + + /* + * Tricky - we space the CPU field according to the max + * number of online CPUs. On a 2-cpu system it would take + * a maximum of 1 digit - on a 128 cpu system it would + * take up to 3 digits: + */ + for (i = 0; i < log10_all - log10_this; i++) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + ret = trace_seq_printf(s, "%d) ", cpu); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +#define TRACE_GRAPH_PROCINFO_LENGTH 14 + +static enum print_line_t +print_graph_proc(struct trace_seq *s, pid_t pid) +{ + int i; + int ret; + int len; + char comm[8]; + int spaces = 0; + /* sign + log10(MAX_INT) + '\0' */ + char pid_str[11]; + + strncpy(comm, trace_find_cmdline(pid), 7); + comm[7] = '\0'; + sprintf(pid_str, "%d", pid); + + /* 1 stands for the "-" character */ + len = strlen(comm) + strlen(pid_str) + 1; + + if (len < TRACE_GRAPH_PROCINFO_LENGTH) + spaces = TRACE_GRAPH_PROCINFO_LENGTH - len; + + /* First spaces to align center */ + for (i = 0; i < spaces / 2; i++) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + ret = trace_seq_printf(s, "%s-%s", comm, pid_str); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Last spaces to align center */ + for (i = 0; i < spaces - (spaces / 2); i++) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + return TRACE_TYPE_HANDLED; +} + + +/* If the pid changed since the last trace, output this event */ +static enum print_line_t +verif_pid(struct trace_seq *s, pid_t pid, int cpu) +{ + pid_t prev_pid; + int ret; + + if (last_pid[cpu] != -1 && last_pid[cpu] == pid) + return TRACE_TYPE_HANDLED; + + prev_pid = last_pid[cpu]; + last_pid[cpu] = pid; + +/* + * Context-switch trace line: + + ------------------------------------------ + | 1) migration/0--1 => sshd-1755 + ------------------------------------------ + + */ + ret = trace_seq_printf(s, + " ------------------------------------------\n"); + if (!ret) + TRACE_TYPE_PARTIAL_LINE; + + ret = print_graph_cpu(s, cpu); + if (ret == TRACE_TYPE_PARTIAL_LINE) + TRACE_TYPE_PARTIAL_LINE; + + ret = print_graph_proc(s, prev_pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_printf(s, " => "); + if (!ret) + TRACE_TYPE_PARTIAL_LINE; + + ret = print_graph_proc(s, pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_printf(s, + "\n ------------------------------------------\n\n"); + if (!ret) + TRACE_TYPE_PARTIAL_LINE; + + return ret; +} + +static bool +trace_branch_is_leaf(struct trace_iterator *iter, + struct ftrace_graph_ent_entry *curr) +{ + struct ring_buffer_iter *ring_iter; + struct ring_buffer_event *event; + struct ftrace_graph_ret_entry *next; + + ring_iter = iter->buffer_iter[iter->cpu]; + + if (!ring_iter) + return false; + + event = ring_buffer_iter_peek(ring_iter, NULL); + + if (!event) + return false; + + next = ring_buffer_event_data(event); + + if (next->ent.type != TRACE_GRAPH_RET) + return false; + + if (curr->ent.pid != next->ent.pid || + curr->graph_ent.func != next->ret.func) + return false; + + return true; +} + +static enum print_line_t +print_graph_irq(struct trace_seq *s, unsigned long addr, + enum trace_type type, int cpu, pid_t pid) +{ + int ret; + + if (addr < (unsigned long)__irqentry_text_start || + addr >= (unsigned long)__irqentry_text_end) + return TRACE_TYPE_UNHANDLED; + + if (type == TRACE_GRAPH_ENT) { + ret = trace_seq_printf(s, "==========> | "); + } else { + /* Cpu */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { + ret = print_graph_cpu(s, cpu); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + /* Proc */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { + ret = print_graph_proc(s, pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_printf(s, " | "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* No overhead */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + ret = trace_seq_printf(s, "<========== |\n"); + } + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +print_graph_duration(unsigned long long duration, struct trace_seq *s) +{ + unsigned long nsecs_rem = do_div(duration, 1000); + /* log10(ULONG_MAX) + '\0' */ + char msecs_str[21]; + char nsecs_str[5]; + int ret, len; + int i; + + sprintf(msecs_str, "%lu", (unsigned long) duration); + + /* Print msecs */ + ret = trace_seq_printf(s, msecs_str); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + len = strlen(msecs_str); + + /* Print nsecs (we don't want to exceed 7 numbers) */ + if (len < 7) { + snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem); + ret = trace_seq_printf(s, ".%s", nsecs_str); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + len += strlen(nsecs_str); + } + + ret = trace_seq_printf(s, " us "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Print remaining spaces to fit the row's width */ + for (i = len; i < 7; i++) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + ret = trace_seq_printf(s, "| "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_HANDLED; + +} + +/* Signal a overhead of time execution to the output */ +static int +print_graph_overhead(unsigned long long duration, struct trace_seq *s) +{ + /* Duration exceeded 100 msecs */ + if (duration > 100000ULL) + return trace_seq_printf(s, "! "); + + /* Duration exceeded 10 msecs */ + if (duration > 10000ULL) + return trace_seq_printf(s, "+ "); + + return trace_seq_printf(s, " "); +} + +/* Case of a leaf function on its call entry */ +static enum print_line_t +print_graph_entry_leaf(struct trace_iterator *iter, + struct ftrace_graph_ent_entry *entry, struct trace_seq *s) +{ + struct ftrace_graph_ret_entry *ret_entry; + struct ftrace_graph_ret *graph_ret; + struct ring_buffer_event *event; + struct ftrace_graph_ent *call; + unsigned long long duration; + int ret; + int i; + + event = ring_buffer_read(iter->buffer_iter[iter->cpu], NULL); + ret_entry = ring_buffer_event_data(event); + graph_ret = &ret_entry->ret; + call = &entry->graph_ent; + duration = graph_ret->rettime - graph_ret->calltime; + + /* Overhead */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { + ret = print_graph_overhead(duration, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* Duration */ + ret = print_graph_duration(duration, s); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + /* Function */ + for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + ret = seq_print_ip_sym(s, call->func, 0); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_printf(s, "();\n"); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +print_graph_entry_nested(struct ftrace_graph_ent_entry *entry, + struct trace_seq *s, pid_t pid, int cpu) +{ + int i; + int ret; + struct ftrace_graph_ent *call = &entry->graph_ent; + + /* No overhead */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* Interrupt */ + ret = print_graph_irq(s, call->func, TRACE_GRAPH_ENT, cpu, pid); + if (ret == TRACE_TYPE_UNHANDLED) { + /* No time */ + ret = trace_seq_printf(s, " | "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } else { + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + + + /* Function */ + for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + ret = seq_print_ip_sym(s, call->func, 0); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_printf(s, "() {\n"); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s, + struct trace_iterator *iter, int cpu) +{ + int ret; + struct trace_entry *ent = iter->ent; + + /* Pid */ + if (verif_pid(s, ent->pid, cpu) == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + /* Cpu */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { + ret = print_graph_cpu(s, cpu); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* Proc */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { + ret = print_graph_proc(s, ent->pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_printf(s, " | "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + if (trace_branch_is_leaf(iter, field)) + return print_graph_entry_leaf(iter, field, s); + else + return print_graph_entry_nested(field, s, iter->ent->pid, cpu); + +} + +static enum print_line_t +print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, + struct trace_entry *ent, int cpu) +{ + int i; + int ret; + unsigned long long duration = trace->rettime - trace->calltime; + + /* Pid */ + if (verif_pid(s, ent->pid, cpu) == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + /* Cpu */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { + ret = print_graph_cpu(s, cpu); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* Proc */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { + ret = print_graph_proc(s, ent->pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_printf(s, " | "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* Overhead */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { + ret = print_graph_overhead(duration, s); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* Duration */ + ret = print_graph_duration(duration, s); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + /* Closing brace */ + for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + ret = trace_seq_printf(s, "}\n"); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Overrun */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) { + ret = trace_seq_printf(s, " (Overruns: %lu)\n", + trace->overrun); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + ret = print_graph_irq(s, trace->func, TRACE_GRAPH_RET, cpu, ent->pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t +print_graph_comment(struct print_entry *trace, struct trace_seq *s, + struct trace_entry *ent, struct trace_iterator *iter) +{ + int i; + int ret; + + /* Pid */ + if (verif_pid(s, ent->pid, iter->cpu) == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + /* Cpu */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) { + ret = print_graph_cpu(s, iter->cpu); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* Proc */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) { + ret = print_graph_proc(s, ent->pid); + if (ret == TRACE_TYPE_PARTIAL_LINE) + return TRACE_TYPE_PARTIAL_LINE; + + ret = trace_seq_printf(s, " | "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* No overhead */ + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* No time */ + ret = trace_seq_printf(s, " | "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + /* Indentation */ + if (trace->depth > 0) + for (i = 0; i < (trace->depth + 1) * TRACE_GRAPH_INDENT; i++) { + ret = trace_seq_printf(s, " "); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + } + + /* The comment */ + ret = trace_seq_printf(s, "/* %s", trace->buf); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + if (ent->flags & TRACE_FLAG_CONT) + trace_seq_print_cont(s, iter); + + ret = trace_seq_printf(s, " */\n"); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + + +enum print_line_t +print_graph_function(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + + switch (entry->type) { + case TRACE_GRAPH_ENT: { + struct ftrace_graph_ent_entry *field; + trace_assign_type(field, entry); + return print_graph_entry(field, s, iter, + iter->cpu); + } + case TRACE_GRAPH_RET: { + struct ftrace_graph_ret_entry *field; + trace_assign_type(field, entry); + return print_graph_return(&field->ret, s, entry, iter->cpu); + } + case TRACE_PRINT: { + struct print_entry *field; + trace_assign_type(field, entry); + return print_graph_comment(field, s, entry, iter); + } + default: + return TRACE_TYPE_UNHANDLED; + } +} + +static void print_graph_headers(struct seq_file *s) +{ + /* 1st line */ + seq_printf(s, "# "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) + seq_printf(s, "CPU "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) + seq_printf(s, "TASK/PID "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) + seq_printf(s, "OVERHEAD/"); + seq_printf(s, "DURATION FUNCTION CALLS\n"); + + /* 2nd line */ + seq_printf(s, "# "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_CPU) + seq_printf(s, "| "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_PROC) + seq_printf(s, "| | "); + if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERHEAD) { + seq_printf(s, "| "); + seq_printf(s, "| | | | |\n"); + } else + seq_printf(s, " | | | | |\n"); +} +static struct tracer graph_trace __read_mostly = { + .name = "function_graph", + .init = graph_trace_init, + .reset = graph_trace_reset, + .print_line = print_graph_function, + .print_header = print_graph_headers, + .flags = &tracer_flags, +}; + +static __init int init_graph_trace(void) +{ + return register_tracer(&graph_trace); +} + +device_initcall(init_graph_trace); diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c new file mode 100644 index 0000000..649df22 --- /dev/null +++ b/kernel/trace/trace_hw_branches.c @@ -0,0 +1,195 @@ +/* + * h/w branch tracer for x86 based on bts + * + * Copyright (C) 2008 Markus Metzger <markus.t.metzger@gmail.com> + * + */ + +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <linux/ftrace.h> +#include <linux/kallsyms.h> + +#include <asm/ds.h> + +#include "trace.h" + + +#define SIZEOF_BTS (1 << 13) + +static DEFINE_PER_CPU(struct bts_tracer *, tracer); +static DEFINE_PER_CPU(unsigned char[SIZEOF_BTS], buffer); + +#define this_tracer per_cpu(tracer, smp_processor_id()) +#define this_buffer per_cpu(buffer, smp_processor_id()) + + +static void bts_trace_start_cpu(void *arg) +{ + if (this_tracer) + ds_release_bts(this_tracer); + + this_tracer = + ds_request_bts(/* task = */ NULL, this_buffer, SIZEOF_BTS, + /* ovfl = */ NULL, /* th = */ (size_t)-1, + BTS_KERNEL); + if (IS_ERR(this_tracer)) { + this_tracer = NULL; + return; + } +} + +static void bts_trace_start(struct trace_array *tr) +{ + int cpu; + + tracing_reset_online_cpus(tr); + + for_each_cpu(cpu, cpu_possible_mask) + smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1); +} + +static void bts_trace_stop_cpu(void *arg) +{ + if (this_tracer) { + ds_release_bts(this_tracer); + this_tracer = NULL; + } +} + +static void bts_trace_stop(struct trace_array *tr) +{ + int cpu; + + for_each_cpu(cpu, cpu_possible_mask) + smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1); +} + +static int bts_trace_init(struct trace_array *tr) +{ + tracing_reset_online_cpus(tr); + bts_trace_start(tr); + + return 0; +} + +static void bts_trace_print_header(struct seq_file *m) +{ + seq_puts(m, + "# CPU# FROM TO FUNCTION\n"); + seq_puts(m, + "# | | | |\n"); +} + +static enum print_line_t bts_trace_print_line(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + struct trace_seq *seq = &iter->seq; + struct hw_branch_entry *it; + + trace_assign_type(it, entry); + + if (entry->type == TRACE_HW_BRANCHES) { + if (trace_seq_printf(seq, "%4d ", entry->cpu) && + trace_seq_printf(seq, "0x%016llx -> 0x%016llx ", + it->from, it->to) && + (!it->from || + seq_print_ip_sym(seq, it->from, /* sym_flags = */ 0)) && + trace_seq_printf(seq, "\n")) + return TRACE_TYPE_HANDLED; + return TRACE_TYPE_PARTIAL_LINE;; + } + return TRACE_TYPE_UNHANDLED; +} + +void trace_hw_branch(struct trace_array *tr, u64 from, u64 to) +{ + struct ring_buffer_event *event; + struct hw_branch_entry *entry; + unsigned long irq; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), &irq); + if (!event) + return; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, 0, from); + entry->ent.type = TRACE_HW_BRANCHES; + entry->ent.cpu = smp_processor_id(); + entry->from = from; + entry->to = to; + ring_buffer_unlock_commit(tr->buffer, event, irq); +} + +static void trace_bts_at(struct trace_array *tr, + const struct bts_trace *trace, void *at) +{ + struct bts_struct bts; + int err = 0; + + WARN_ON_ONCE(!trace->read); + if (!trace->read) + return; + + err = trace->read(this_tracer, at, &bts); + if (err < 0) + return; + + switch (bts.qualifier) { + case BTS_BRANCH: + trace_hw_branch(tr, bts.variant.lbr.from, bts.variant.lbr.to); + break; + } +} + +static void trace_bts_cpu(void *arg) +{ + struct trace_array *tr = (struct trace_array *) arg; + const struct bts_trace *trace; + unsigned char *at; + + if (!this_tracer) + return; + + ds_suspend_bts(this_tracer); + trace = ds_read_bts(this_tracer); + if (!trace) + goto out; + + for (at = trace->ds.top; (void *)at < trace->ds.end; + at += trace->ds.size) + trace_bts_at(tr, trace, at); + + for (at = trace->ds.begin; (void *)at < trace->ds.top; + at += trace->ds.size) + trace_bts_at(tr, trace, at); + +out: + ds_resume_bts(this_tracer); +} + +static void trace_bts_prepare(struct trace_iterator *iter) +{ + int cpu; + + for_each_cpu(cpu, cpu_possible_mask) + smp_call_function_single(cpu, trace_bts_cpu, iter->tr, 1); +} + +struct tracer bts_tracer __read_mostly = +{ + .name = "hw-branch-tracer", + .init = bts_trace_init, + .reset = bts_trace_stop, + .print_header = bts_trace_print_header, + .print_line = bts_trace_print_line, + .start = bts_trace_start, + .stop = bts_trace_stop, + .open = trace_bts_prepare +}; + +__init static int init_bts_trace(void) +{ + return register_tracer(&bts_tracer); +} +device_initcall(init_bts_trace); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 9c74071..7c2e326 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -353,15 +353,28 @@ void trace_preempt_off(unsigned long a0, unsigned long a1) } #endif /* CONFIG_PREEMPT_TRACER */ +/* + * save_tracer_enabled is used to save the state of the tracer_enabled + * variable when we disable it when we open a trace output file. + */ +static int save_tracer_enabled; + static void start_irqsoff_tracer(struct trace_array *tr) { register_ftrace_function(&trace_ops); - tracer_enabled = 1; + if (tracing_is_enabled()) { + tracer_enabled = 1; + save_tracer_enabled = 1; + } else { + tracer_enabled = 0; + save_tracer_enabled = 0; + } } static void stop_irqsoff_tracer(struct trace_array *tr) { tracer_enabled = 0; + save_tracer_enabled = 0; unregister_ftrace_function(&trace_ops); } @@ -370,53 +383,55 @@ static void __irqsoff_tracer_init(struct trace_array *tr) irqsoff_trace = tr; /* make sure that the tracer is visible */ smp_wmb(); - - if (tr->ctrl) - start_irqsoff_tracer(tr); + start_irqsoff_tracer(tr); } static void irqsoff_tracer_reset(struct trace_array *tr) { - if (tr->ctrl) - stop_irqsoff_tracer(tr); + stop_irqsoff_tracer(tr); } -static void irqsoff_tracer_ctrl_update(struct trace_array *tr) +static void irqsoff_tracer_start(struct trace_array *tr) { - if (tr->ctrl) - start_irqsoff_tracer(tr); - else - stop_irqsoff_tracer(tr); + tracer_enabled = 1; + save_tracer_enabled = 1; +} + +static void irqsoff_tracer_stop(struct trace_array *tr) +{ + tracer_enabled = 0; + save_tracer_enabled = 0; } static void irqsoff_tracer_open(struct trace_iterator *iter) { /* stop the trace while dumping */ - if (iter->tr->ctrl) - stop_irqsoff_tracer(iter->tr); + tracer_enabled = 0; } static void irqsoff_tracer_close(struct trace_iterator *iter) { - if (iter->tr->ctrl) - start_irqsoff_tracer(iter->tr); + /* restart tracing */ + tracer_enabled = save_tracer_enabled; } #ifdef CONFIG_IRQSOFF_TRACER -static void irqsoff_tracer_init(struct trace_array *tr) +static int irqsoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_IRQS_OFF; __irqsoff_tracer_init(tr); + return 0; } static struct tracer irqsoff_tracer __read_mostly = { .name = "irqsoff", .init = irqsoff_tracer_init, .reset = irqsoff_tracer_reset, + .start = irqsoff_tracer_start, + .stop = irqsoff_tracer_stop, .open = irqsoff_tracer_open, .close = irqsoff_tracer_close, - .ctrl_update = irqsoff_tracer_ctrl_update, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_irqsoff, @@ -428,11 +443,12 @@ static struct tracer irqsoff_tracer __read_mostly = #endif #ifdef CONFIG_PREEMPT_TRACER -static void preemptoff_tracer_init(struct trace_array *tr) +static int preemptoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_PREEMPT_OFF; __irqsoff_tracer_init(tr); + return 0; } static struct tracer preemptoff_tracer __read_mostly = @@ -440,9 +456,10 @@ static struct tracer preemptoff_tracer __read_mostly = .name = "preemptoff", .init = preemptoff_tracer_init, .reset = irqsoff_tracer_reset, + .start = irqsoff_tracer_start, + .stop = irqsoff_tracer_stop, .open = irqsoff_tracer_open, .close = irqsoff_tracer_close, - .ctrl_update = irqsoff_tracer_ctrl_update, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptoff, @@ -456,11 +473,12 @@ static struct tracer preemptoff_tracer __read_mostly = #if defined(CONFIG_IRQSOFF_TRACER) && \ defined(CONFIG_PREEMPT_TRACER) -static void preemptirqsoff_tracer_init(struct trace_array *tr) +static int preemptirqsoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF; __irqsoff_tracer_init(tr); + return 0; } static struct tracer preemptirqsoff_tracer __read_mostly = @@ -468,9 +486,10 @@ static struct tracer preemptirqsoff_tracer __read_mostly = .name = "preemptirqsoff", .init = preemptirqsoff_tracer_init, .reset = irqsoff_tracer_reset, + .start = irqsoff_tracer_start, + .stop = irqsoff_tracer_stop, .open = irqsoff_tracer_open, .close = irqsoff_tracer_close, - .ctrl_update = irqsoff_tracer_ctrl_update, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptirqsoff, diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index e62cbf7..fffcb06 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -22,44 +22,35 @@ static unsigned long prev_overruns; static void mmio_reset_data(struct trace_array *tr) { - int cpu; - overrun_detected = false; prev_overruns = 0; - tr->time_start = ftrace_now(tr->cpu); - for_each_online_cpu(cpu) - tracing_reset(tr, cpu); + tracing_reset_online_cpus(tr); } -static void mmio_trace_init(struct trace_array *tr) +static int mmio_trace_init(struct trace_array *tr) { pr_debug("in %s\n", __func__); mmio_trace_array = tr; - if (tr->ctrl) { - mmio_reset_data(tr); - enable_mmiotrace(); - } + + mmio_reset_data(tr); + enable_mmiotrace(); + return 0; } static void mmio_trace_reset(struct trace_array *tr) { pr_debug("in %s\n", __func__); - if (tr->ctrl) - disable_mmiotrace(); + + disable_mmiotrace(); mmio_reset_data(tr); mmio_trace_array = NULL; } -static void mmio_trace_ctrl_update(struct trace_array *tr) +static void mmio_trace_start(struct trace_array *tr) { pr_debug("in %s\n", __func__); - if (tr->ctrl) { - mmio_reset_data(tr); - enable_mmiotrace(); - } else { - disable_mmiotrace(); - } + mmio_reset_data(tr); } static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev) @@ -296,10 +287,10 @@ static struct tracer mmio_tracer __read_mostly = .name = "mmiotrace", .init = mmio_trace_init, .reset = mmio_trace_reset, + .start = mmio_trace_start, .pipe_open = mmio_pipe_open, .close = mmio_close, .read = mmio_read, - .ctrl_update = mmio_trace_ctrl_update, .print_line = mmio_print_line, }; @@ -371,5 +362,5 @@ void mmio_trace_mapping(struct mmiotrace_map *map) int mmio_trace_printk(const char *fmt, va_list args) { - return trace_vprintk(0, fmt, args); + return trace_vprintk(0, -1, fmt, args); } diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index 4592b48..b9767ac 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -12,6 +12,27 @@ #include "trace.h" +/* Our two options */ +enum { + TRACE_NOP_OPT_ACCEPT = 0x1, + TRACE_NOP_OPT_REFUSE = 0x2 +}; + +/* Options for the tracer (see trace_options file) */ +static struct tracer_opt nop_opts[] = { + /* Option that will be accepted by set_flag callback */ + { TRACER_OPT(test_nop_accept, TRACE_NOP_OPT_ACCEPT) }, + /* Option that will be refused by set_flag callback */ + { TRACER_OPT(test_nop_refuse, TRACE_NOP_OPT_REFUSE) }, + { } /* Always set a last empty entry */ +}; + +static struct tracer_flags nop_flags = { + /* You can check your flags value here when you want. */ + .val = 0, /* By default: all flags disabled */ + .opts = nop_opts +}; + static struct trace_array *ctx_trace; static void start_nop_trace(struct trace_array *tr) @@ -24,7 +45,7 @@ static void stop_nop_trace(struct trace_array *tr) /* Nothing to do! */ } -static void nop_trace_init(struct trace_array *tr) +static int nop_trace_init(struct trace_array *tr) { int cpu; ctx_trace = tr; @@ -32,33 +53,53 @@ static void nop_trace_init(struct trace_array *tr) for_each_online_cpu(cpu) tracing_reset(tr, cpu); - if (tr->ctrl) - start_nop_trace(tr); + start_nop_trace(tr); + return 0; } static void nop_trace_reset(struct trace_array *tr) { - if (tr->ctrl) - stop_nop_trace(tr); + stop_nop_trace(tr); } -static void nop_trace_ctrl_update(struct trace_array *tr) +/* It only serves as a signal handler and a callback to + * accept or refuse tthe setting of a flag. + * If you don't implement it, then the flag setting will be + * automatically accepted. + */ +static int nop_set_flag(u32 old_flags, u32 bit, int set) { - /* When starting a new trace, reset the buffers */ - if (tr->ctrl) - start_nop_trace(tr); - else - stop_nop_trace(tr); + /* + * Note that you don't need to update nop_flags.val yourself. + * The tracing Api will do it automatically if you return 0 + */ + if (bit == TRACE_NOP_OPT_ACCEPT) { + printk(KERN_DEBUG "nop_test_accept flag set to %d: we accept." + " Now cat trace_options to see the result\n", + set); + return 0; + } + + if (bit == TRACE_NOP_OPT_REFUSE) { + printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse." + "Now cat trace_options to see the result\n", + set); + return -EINVAL; + } + + return 0; } + struct tracer nop_trace __read_mostly = { .name = "nop", .init = nop_trace_init, .reset = nop_trace_reset, - .ctrl_update = nop_trace_ctrl_update, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_nop, #endif + .flags = &nop_flags, + .set_flag = nop_set_flag }; diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c new file mode 100644 index 0000000..7bda248 --- /dev/null +++ b/kernel/trace/trace_power.c @@ -0,0 +1,179 @@ +/* + * ring buffer based C-state tracer + * + * Arjan van de Ven <arjan@linux.intel.com> + * Copyright (C) 2008 Intel Corporation + * + * Much is borrowed from trace_boot.c which is + * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com> + * + */ + +#include <linux/init.h> +#include <linux/debugfs.h> +#include <linux/ftrace.h> +#include <linux/kallsyms.h> +#include <linux/module.h> + +#include "trace.h" + +static struct trace_array *power_trace; +static int __read_mostly trace_power_enabled; + + +static void start_power_trace(struct trace_array *tr) +{ + trace_power_enabled = 1; +} + +static void stop_power_trace(struct trace_array *tr) +{ + trace_power_enabled = 0; +} + + +static int power_trace_init(struct trace_array *tr) +{ + int cpu; + power_trace = tr; + + trace_power_enabled = 1; + + for_each_cpu(cpu, cpu_possible_mask) + tracing_reset(tr, cpu); + return 0; +} + +static enum print_line_t power_print_line(struct trace_iterator *iter) +{ + int ret = 0; + struct trace_entry *entry = iter->ent; + struct trace_power *field ; + struct power_trace *it; + struct trace_seq *s = &iter->seq; + struct timespec stamp; + struct timespec duration; + + trace_assign_type(field, entry); + it = &field->state_data; + stamp = ktime_to_timespec(it->stamp); + duration = ktime_to_timespec(ktime_sub(it->end, it->stamp)); + + if (entry->type == TRACE_POWER) { + if (it->type == POWER_CSTATE) + ret = trace_seq_printf(s, "[%5ld.%09ld] CSTATE: Going to C%i on cpu %i for %ld.%09ld\n", + stamp.tv_sec, + stamp.tv_nsec, + it->state, iter->cpu, + duration.tv_sec, + duration.tv_nsec); + if (it->type == POWER_PSTATE) + ret = trace_seq_printf(s, "[%5ld.%09ld] PSTATE: Going to P%i on cpu %i\n", + stamp.tv_sec, + stamp.tv_nsec, + it->state, iter->cpu); + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + return TRACE_TYPE_HANDLED; + } + return TRACE_TYPE_UNHANDLED; +} + +static struct tracer power_tracer __read_mostly = +{ + .name = "power", + .init = power_trace_init, + .start = start_power_trace, + .stop = stop_power_trace, + .reset = stop_power_trace, + .print_line = power_print_line, +}; + +static int init_power_trace(void) +{ + return register_tracer(&power_tracer); +} +device_initcall(init_power_trace); + +void trace_power_start(struct power_trace *it, unsigned int type, + unsigned int level) +{ + if (!trace_power_enabled) + return; + + memset(it, 0, sizeof(struct power_trace)); + it->state = level; + it->type = type; + it->stamp = ktime_get(); +} +EXPORT_SYMBOL_GPL(trace_power_start); + + +void trace_power_end(struct power_trace *it) +{ + struct ring_buffer_event *event; + struct trace_power *entry; + struct trace_array_cpu *data; + unsigned long irq_flags; + struct trace_array *tr = power_trace; + + if (!trace_power_enabled) + return; + + preempt_disable(); + it->end = ktime_get(); + data = tr->data[smp_processor_id()]; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, 0, 0); + entry->ent.type = TRACE_POWER; + entry->state_data = *it; + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + + trace_wake_up(); + + out: + preempt_enable(); +} +EXPORT_SYMBOL_GPL(trace_power_end); + +void trace_power_mark(struct power_trace *it, unsigned int type, + unsigned int level) +{ + struct ring_buffer_event *event; + struct trace_power *entry; + struct trace_array_cpu *data; + unsigned long irq_flags; + struct trace_array *tr = power_trace; + + if (!trace_power_enabled) + return; + + memset(it, 0, sizeof(struct power_trace)); + it->state = level; + it->type = type; + it->stamp = ktime_get(); + preempt_disable(); + it->end = it->stamp; + data = tr->data[smp_processor_id()]; + + event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry), + &irq_flags); + if (!event) + goto out; + entry = ring_buffer_event_data(event); + tracing_generic_entry_update(&entry->ent, 0, 0); + entry->ent.type = TRACE_POWER; + entry->state_data = *it; + ring_buffer_unlock_commit(tr->buffer, event, irq_flags); + + trace_wake_up(); + + out: + preempt_enable(); +} +EXPORT_SYMBOL_GPL(trace_power_mark); diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index b8f56be..df175cb 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -16,7 +16,8 @@ static struct trace_array *ctx_trace; static int __read_mostly tracer_enabled; -static atomic_t sched_ref; +static int sched_ref; +static DEFINE_MUTEX(sched_register_mutex); static void probe_sched_switch(struct rq *__rq, struct task_struct *prev, @@ -27,7 +28,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev, int cpu; int pc; - if (!atomic_read(&sched_ref)) + if (!sched_ref) return; tracing_record_cmdline(prev); @@ -48,7 +49,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev, } static void -probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee) +probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success) { struct trace_array_cpu *data; unsigned long flags; @@ -71,16 +72,6 @@ probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee) local_irq_restore(flags); } -static void sched_switch_reset(struct trace_array *tr) -{ - int cpu; - - tr->time_start = ftrace_now(tr->cpu); - - for_each_online_cpu(cpu) - tracing_reset(tr, cpu); -} - static int tracing_sched_register(void) { int ret; @@ -123,20 +114,18 @@ static void tracing_sched_unregister(void) static void tracing_start_sched_switch(void) { - long ref; - - ref = atomic_inc_return(&sched_ref); - if (ref == 1) + mutex_lock(&sched_register_mutex); + if (!(sched_ref++)) tracing_sched_register(); + mutex_unlock(&sched_register_mutex); } static void tracing_stop_sched_switch(void) { - long ref; - - ref = atomic_dec_and_test(&sched_ref); - if (ref) + mutex_lock(&sched_register_mutex); + if (!(--sched_ref)) tracing_sched_unregister(); + mutex_unlock(&sched_register_mutex); } void tracing_start_cmdline_record(void) @@ -149,40 +138,86 @@ void tracing_stop_cmdline_record(void) tracing_stop_sched_switch(); } +/** + * tracing_start_sched_switch_record - start tracing context switches + * + * Turns on context switch tracing for a tracer. + */ +void tracing_start_sched_switch_record(void) +{ + if (unlikely(!ctx_trace)) { + WARN_ON(1); + return; + } + + tracing_start_sched_switch(); + + mutex_lock(&sched_register_mutex); + tracer_enabled++; + mutex_unlock(&sched_register_mutex); +} + +/** + * tracing_stop_sched_switch_record - start tracing context switches + * + * Turns off context switch tracing for a tracer. + */ +void tracing_stop_sched_switch_record(void) +{ + mutex_lock(&sched_register_mutex); + tracer_enabled--; + WARN_ON(tracer_enabled < 0); + mutex_unlock(&sched_register_mutex); + + tracing_stop_sched_switch(); +} + +/** + * tracing_sched_switch_assign_trace - assign a trace array for ctx switch + * @tr: trace array pointer to assign + * + * Some tracers might want to record the context switches in their + * trace. This function lets those tracers assign the trace array + * to use. + */ +void tracing_sched_switch_assign_trace(struct trace_array *tr) +{ + ctx_trace = tr; +} + static void start_sched_trace(struct trace_array *tr) { - sched_switch_reset(tr); - tracing_start_cmdline_record(); - tracer_enabled = 1; + tracing_reset_online_cpus(tr); + tracing_start_sched_switch_record(); } static void stop_sched_trace(struct trace_array *tr) { - tracer_enabled = 0; - tracing_stop_cmdline_record(); + tracing_stop_sched_switch_record(); } -static void sched_switch_trace_init(struct trace_array *tr) +static int sched_switch_trace_init(struct trace_array *tr) { ctx_trace = tr; - - if (tr->ctrl) - start_sched_trace(tr); + start_sched_trace(tr); + return 0; } static void sched_switch_trace_reset(struct trace_array *tr) { - if (tr->ctrl) + if (sched_ref) stop_sched_trace(tr); } -static void sched_switch_trace_ctrl_update(struct trace_array *tr) +static void sched_switch_trace_start(struct trace_array *tr) { - /* When starting a new trace, reset the buffers */ - if (tr->ctrl) - start_sched_trace(tr); - else - stop_sched_trace(tr); + tracing_reset_online_cpus(tr); + tracing_start_sched_switch(); +} + +static void sched_switch_trace_stop(struct trace_array *tr) +{ + tracing_stop_sched_switch(); } static struct tracer sched_switch_trace __read_mostly = @@ -190,7 +225,8 @@ static struct tracer sched_switch_trace __read_mostly = .name = "sched_switch", .init = sched_switch_trace_init, .reset = sched_switch_trace_reset, - .ctrl_update = sched_switch_trace_ctrl_update, + .start = sched_switch_trace_start, + .stop = sched_switch_trace_stop, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_sched_switch, #endif @@ -198,14 +234,7 @@ static struct tracer sched_switch_trace __read_mostly = __init static int init_sched_switch_trace(void) { - int ret = 0; - - if (atomic_read(&sched_ref)) - ret = tracing_sched_register(); - if (ret) { - pr_info("error registering scheduler trace\n"); - return ret; - } return register_tracer(&sched_switch_trace); } device_initcall(init_sched_switch_trace); + diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 3ae93f1..43586b6 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -50,8 +50,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) return; pc = preempt_count(); - resched = need_resched(); - preempt_disable_notrace(); + resched = ftrace_preempt_disable(); cpu = raw_smp_processor_id(); data = tr->data[cpu]; @@ -81,15 +80,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) out: atomic_dec(&data->disabled); - /* - * To prevent recursion from the scheduler, if the - * resched flag was set before we entered, then - * don't reschedule. - */ - if (resched) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); + ftrace_preempt_enable(resched); } static struct ftrace_ops trace_ops __read_mostly = @@ -220,7 +211,7 @@ static void wakeup_reset(struct trace_array *tr) } static void -probe_wakeup(struct rq *rq, struct task_struct *p) +probe_wakeup(struct rq *rq, struct task_struct *p, int success) { int cpu = smp_processor_id(); unsigned long flags; @@ -271,6 +262,12 @@ out: atomic_dec(&wakeup_trace->data[cpu]->disabled); } +/* + * save_tracer_enabled is used to save the state of the tracer_enabled + * variable when we disable it when we open a trace output file. + */ +static int save_tracer_enabled; + static void start_wakeup_tracer(struct trace_array *tr) { int ret; @@ -309,7 +306,13 @@ static void start_wakeup_tracer(struct trace_array *tr) register_ftrace_function(&trace_ops); - tracer_enabled = 1; + if (tracing_is_enabled()) { + tracer_enabled = 1; + save_tracer_enabled = 1; + } else { + tracer_enabled = 0; + save_tracer_enabled = 0; + } return; fail_deprobe_wake_new: @@ -321,49 +324,53 @@ fail_deprobe: static void stop_wakeup_tracer(struct trace_array *tr) { tracer_enabled = 0; + save_tracer_enabled = 0; unregister_ftrace_function(&trace_ops); unregister_trace_sched_switch(probe_wakeup_sched_switch); unregister_trace_sched_wakeup_new(probe_wakeup); unregister_trace_sched_wakeup(probe_wakeup); } -static void wakeup_tracer_init(struct trace_array *tr) +static int wakeup_tracer_init(struct trace_array *tr) { wakeup_trace = tr; - - if (tr->ctrl) - start_wakeup_tracer(tr); + start_wakeup_tracer(tr); + return 0; } static void wakeup_tracer_reset(struct trace_array *tr) { - if (tr->ctrl) { - stop_wakeup_tracer(tr); - /* make sure we put back any tasks we are tracing */ - wakeup_reset(tr); - } + stop_wakeup_tracer(tr); + /* make sure we put back any tasks we are tracing */ + wakeup_reset(tr); +} + +static void wakeup_tracer_start(struct trace_array *tr) +{ + wakeup_reset(tr); + tracer_enabled = 1; + save_tracer_enabled = 1; } -static void wakeup_tracer_ctrl_update(struct trace_array *tr) +static void wakeup_tracer_stop(struct trace_array *tr) { - if (tr->ctrl) - start_wakeup_tracer(tr); - else - stop_wakeup_tracer(tr); + tracer_enabled = 0; + save_tracer_enabled = 0; } static void wakeup_tracer_open(struct trace_iterator *iter) { /* stop the trace while dumping */ - if (iter->tr->ctrl) - stop_wakeup_tracer(iter->tr); + tracer_enabled = 0; } static void wakeup_tracer_close(struct trace_iterator *iter) { /* forget about any processes we were recording */ - if (iter->tr->ctrl) - start_wakeup_tracer(iter->tr); + if (save_tracer_enabled) { + wakeup_reset(iter->tr); + tracer_enabled = 1; + } } static struct tracer wakeup_tracer __read_mostly = @@ -371,9 +378,10 @@ static struct tracer wakeup_tracer __read_mostly = .name = "wakeup", .init = wakeup_tracer_init, .reset = wakeup_tracer_reset, + .start = wakeup_tracer_start, + .stop = wakeup_tracer_stop, .open = wakeup_tracer_open, .close = wakeup_tracer_close, - .ctrl_update = wakeup_tracer_ctrl_update, .print_max = 1, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 90bc752..88c8eb7 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -13,6 +13,7 @@ static inline int trace_valid_entry(struct trace_entry *entry) case TRACE_STACK: case TRACE_PRINT: case TRACE_SPECIAL: + case TRACE_BRANCH: return 1; } return 0; @@ -51,7 +52,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) int cpu, ret = 0; /* Don't allow flipping of max traces now */ - raw_local_irq_save(flags); + local_irq_save(flags); __raw_spin_lock(&ftrace_max_lock); cnt = ring_buffer_entries(tr->buffer); @@ -62,7 +63,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) break; } __raw_spin_unlock(&ftrace_max_lock); - raw_local_irq_restore(flags); + local_irq_restore(flags); if (count) *count = cnt; @@ -70,6 +71,11 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count) return ret; } +static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) +{ + printk(KERN_WARNING "Failed to init %s tracer, init returned %d\n", + trace->name, init_ret); +} #ifdef CONFIG_FUNCTION_TRACER #ifdef CONFIG_DYNAMIC_FTRACE @@ -110,8 +116,11 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, ftrace_set_filter(func_name, strlen(func_name), 1); /* enable tracing */ - tr->ctrl = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } /* Sleep for a 1/10 of a second */ msleep(100); @@ -134,13 +143,13 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, msleep(100); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); ftrace_enabled = 0; /* check the trace buffer */ ret = trace_test_buffer(tr, &count); trace->reset(tr); + tracing_start(); /* we should only have one item */ if (!ret && count != 1) { @@ -148,6 +157,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, ret = -1; goto out; } + out: ftrace_enabled = save_ftrace_enabled; tracer_enabled = save_tracer_enabled; @@ -180,18 +190,22 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ftrace_enabled = 1; tracer_enabled = 1; - tr->ctrl = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } + /* Sleep for a 1/10 of a second */ msleep(100); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); ftrace_enabled = 0; /* check the trace buffer */ ret = trace_test_buffer(tr, &count); trace->reset(tr); + tracing_start(); if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); @@ -223,8 +237,12 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) int ret; /* start the tracing */ - tr->ctrl = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* reset the max latency */ tracing_max_latency = 0; /* disable interrupts for a bit */ @@ -232,13 +250,13 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) udelay(100); local_irq_enable(); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(tr, NULL); if (!ret) ret = trace_test_buffer(&max_tr, &count); trace->reset(tr); + tracing_start(); if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); @@ -259,9 +277,26 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) unsigned long count; int ret; + /* + * Now that the big kernel lock is no longer preemptable, + * and this is called with the BKL held, it will always + * fail. If preemption is already disabled, simply + * pass the test. When the BKL is removed, or becomes + * preemptible again, we will once again test this, + * so keep it in. + */ + if (preempt_count()) { + printk(KERN_CONT "can not test ... force "); + return 0; + } + /* start the tracing */ - tr->ctrl = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* reset the max latency */ tracing_max_latency = 0; /* disable preemption for a bit */ @@ -269,13 +304,13 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) udelay(100); preempt_enable(); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(tr, NULL); if (!ret) ret = trace_test_buffer(&max_tr, &count); trace->reset(tr); + tracing_start(); if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); @@ -296,9 +331,25 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * unsigned long count; int ret; + /* + * Now that the big kernel lock is no longer preemptable, + * and this is called with the BKL held, it will always + * fail. If preemption is already disabled, simply + * pass the test. When the BKL is removed, or becomes + * preemptible again, we will once again test this, + * so keep it in. + */ + if (preempt_count()) { + printk(KERN_CONT "can not test ... force "); + return 0; + } + /* start the tracing */ - tr->ctrl = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + goto out; + } /* reset the max latency */ tracing_max_latency = 0; @@ -312,27 +363,30 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * local_irq_enable(); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(tr, NULL); - if (ret) + if (ret) { + tracing_start(); goto out; + } ret = trace_test_buffer(&max_tr, &count); - if (ret) + if (ret) { + tracing_start(); goto out; + } if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); ret = -1; + tracing_start(); goto out; } /* do the test by disabling interrupts first this time */ tracing_max_latency = 0; - tr->ctrl = 1; - trace->ctrl_update(tr); + tracing_start(); preempt_disable(); local_irq_disable(); udelay(100); @@ -341,8 +395,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * local_irq_enable(); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(tr, NULL); if (ret) @@ -358,6 +411,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * out: trace->reset(tr); + tracing_start(); tracing_max_latency = save_max; return ret; @@ -423,8 +477,12 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) wait_for_completion(&isrt); /* start the tracing */ - tr->ctrl = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* reset the max latency */ tracing_max_latency = 0; @@ -448,8 +506,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) msleep(100); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); /* check both trace buffers */ ret = trace_test_buffer(tr, NULL); if (!ret) @@ -457,6 +514,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) trace->reset(tr); + tracing_start(); tracing_max_latency = save_max; @@ -480,16 +538,20 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr int ret; /* start the tracing */ - tr->ctrl = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + /* Sleep for a 1/10 of a second */ msleep(100); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); /* check the trace buffer */ ret = trace_test_buffer(tr, &count); trace->reset(tr); + tracing_start(); if (!ret && !count) { printk(KERN_CONT ".. no entries found .."); @@ -508,17 +570,48 @@ trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr) int ret; /* start the tracing */ - tr->ctrl = 1; - trace->init(tr); + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return 0; + } + /* Sleep for a 1/10 of a second */ msleep(100); /* stop the tracing. */ - tr->ctrl = 0; - trace->ctrl_update(tr); + tracing_stop(); /* check the trace buffer */ ret = trace_test_buffer(tr, &count); trace->reset(tr); + tracing_start(); return ret; } #endif /* CONFIG_SYSPROF_TRACER */ + +#ifdef CONFIG_BRANCH_TRACER +int +trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + + /* start the tracing */ + ret = trace->init(tr); + if (ret) { + warn_failed_init_tracer(trace, ret); + return ret; + } + + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tracing_stop(); + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + tracing_start(); + + return ret; +} +#endif /* CONFIG_BRANCH_TRACER */ diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 3bdb44b..d0871bc 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -10,6 +10,7 @@ #include <linux/debugfs.h> #include <linux/ftrace.h> #include <linux/module.h> +#include <linux/sysctl.h> #include <linux/init.h> #include <linux/fs.h> #include "trace.h" @@ -31,6 +32,10 @@ static raw_spinlock_t max_stack_lock = static int stack_trace_disabled __read_mostly; static DEFINE_PER_CPU(int, trace_active); +static DEFINE_MUTEX(stack_sysctl_mutex); + +int stack_tracer_enabled; +static int last_stack_tracer_enabled; static inline void check_stack(void) { @@ -48,7 +53,7 @@ static inline void check_stack(void) if (!object_is_on_stack(&this_size)) return; - raw_local_irq_save(flags); + local_irq_save(flags); __raw_spin_lock(&max_stack_lock); /* a race could have already updated it */ @@ -78,6 +83,7 @@ static inline void check_stack(void) * on a new max, so it is far from a fast path. */ while (i < max_stack_trace.nr_entries) { + int found = 0; stack_dump_index[i] = this_size; p = start; @@ -86,17 +92,19 @@ static inline void check_stack(void) if (*p == stack_dump_trace[i]) { this_size = stack_dump_index[i++] = (top - p) * sizeof(unsigned long); + found = 1; /* Start the search from here */ start = p + 1; } } - i++; + if (!found) + i++; } out: __raw_spin_unlock(&max_stack_lock); - raw_local_irq_restore(flags); + local_irq_restore(flags); } static void @@ -107,8 +115,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) if (unlikely(!ftrace_enabled || stack_trace_disabled)) return; - resched = need_resched(); - preempt_disable_notrace(); + resched = ftrace_preempt_disable(); cpu = raw_smp_processor_id(); /* no atomic needed, we only modify this variable by this cpu */ @@ -120,10 +127,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) out: per_cpu(trace_active, cpu)--; /* prevent recursion in schedule */ - if (resched) - preempt_enable_no_resched_notrace(); - else - preempt_enable_notrace(); + ftrace_preempt_enable(resched); } static struct ftrace_ops trace_ops __read_mostly = @@ -166,16 +170,16 @@ stack_max_size_write(struct file *filp, const char __user *ubuf, if (ret < 0) return ret; - raw_local_irq_save(flags); + local_irq_save(flags); __raw_spin_lock(&max_stack_lock); *ptr = val; __raw_spin_unlock(&max_stack_lock); - raw_local_irq_restore(flags); + local_irq_restore(flags); return count; } -static struct file_operations stack_max_size_fops = { +static const struct file_operations stack_max_size_fops = { .open = tracing_open_generic, .read = stack_max_size_read, .write = stack_max_size_write, @@ -273,7 +277,7 @@ static int t_show(struct seq_file *m, void *v) return 0; } -static struct seq_operations stack_trace_seq_ops = { +static const struct seq_operations stack_trace_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, @@ -289,12 +293,47 @@ static int stack_trace_open(struct inode *inode, struct file *file) return ret; } -static struct file_operations stack_trace_fops = { +static const struct file_operations stack_trace_fops = { .open = stack_trace_open, .read = seq_read, .llseek = seq_lseek, }; +int +stack_trace_sysctl(struct ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + mutex_lock(&stack_sysctl_mutex); + + ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + + if (ret || !write || + (last_stack_tracer_enabled == stack_tracer_enabled)) + goto out; + + last_stack_tracer_enabled = stack_tracer_enabled; + + if (stack_tracer_enabled) + register_ftrace_function(&trace_ops); + else + unregister_ftrace_function(&trace_ops); + + out: + mutex_unlock(&stack_sysctl_mutex); + return ret; +} + +static __init int enable_stacktrace(char *str) +{ + stack_tracer_enabled = 1; + last_stack_tracer_enabled = 1; + return 1; +} +__setup("stacktrace", enable_stacktrace); + static __init int stack_trace_init(void) { struct dentry *d_tracer; @@ -312,7 +351,8 @@ static __init int stack_trace_init(void) if (!entry) pr_warning("Could not create debugfs 'stack_trace' entry\n"); - register_ftrace_function(&trace_ops); + if (stack_tracer_enabled) + register_ftrace_function(&trace_ops); return 0; } diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c index 9587d3b..eaca5ad 100644 --- a/kernel/trace/trace_sysprof.c +++ b/kernel/trace/trace_sysprof.c @@ -196,27 +196,19 @@ static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } -static void start_stack_timer(int cpu) +static void start_stack_timer(void *unused) { - struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu); + struct hrtimer *hrtimer = &__get_cpu_var(stack_trace_hrtimer); hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = stack_trace_timer_fn; - hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL); } static void start_stack_timers(void) { - cpumask_t saved_mask = current->cpus_allowed; - int cpu; - - for_each_online_cpu(cpu) { - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - start_stack_timer(cpu); - } - set_cpus_allowed_ptr(current, &saved_mask); + on_each_cpu(start_stack_timer, NULL, 1); } static void stop_stack_timer(int cpu) @@ -234,20 +226,10 @@ static void stop_stack_timers(void) stop_stack_timer(cpu); } -static void stack_reset(struct trace_array *tr) -{ - int cpu; - - tr->time_start = ftrace_now(tr->cpu); - - for_each_online_cpu(cpu) - tracing_reset(tr, cpu); -} - static void start_stack_trace(struct trace_array *tr) { mutex_lock(&sample_timer_lock); - stack_reset(tr); + tracing_reset_online_cpus(tr); start_stack_timers(); tracer_enabled = 1; mutex_unlock(&sample_timer_lock); @@ -261,27 +243,17 @@ static void stop_stack_trace(struct trace_array *tr) mutex_unlock(&sample_timer_lock); } -static void stack_trace_init(struct trace_array *tr) +static int stack_trace_init(struct trace_array *tr) { sysprof_trace = tr; - if (tr->ctrl) - start_stack_trace(tr); + start_stack_trace(tr); + return 0; } static void stack_trace_reset(struct trace_array *tr) { - if (tr->ctrl) - stop_stack_trace(tr); -} - -static void stack_trace_ctrl_update(struct trace_array *tr) -{ - /* When starting a new trace, reset the buffers */ - if (tr->ctrl) - start_stack_trace(tr); - else - stop_stack_trace(tr); + stop_stack_trace(tr); } static struct tracer stack_trace __read_mostly = @@ -289,7 +261,6 @@ static struct tracer stack_trace __read_mostly = .name = "sysprof", .init = stack_trace_init, .reset = stack_trace_reset, - .ctrl_update = stack_trace_ctrl_update, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_sysprof, #endif diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index af8c856..7960274 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -43,6 +43,7 @@ static DEFINE_MUTEX(tracepoints_mutex); */ #define TRACEPOINT_HASH_BITS 6 #define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS) +static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE]; /* * Note about RCU : @@ -54,40 +55,43 @@ struct tracepoint_entry { struct hlist_node hlist; void **funcs; int refcount; /* Number of times armed. 0 if disarmed. */ - struct rcu_head rcu; - void *oldptr; - unsigned char rcu_pending:1; char name[0]; }; -static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE]; +struct tp_probes { + union { + struct rcu_head rcu; + struct list_head list; + } u; + void *probes[0]; +}; -static void free_old_closure(struct rcu_head *head) +static inline void *allocate_probes(int count) { - struct tracepoint_entry *entry = container_of(head, - struct tracepoint_entry, rcu); - kfree(entry->oldptr); - /* Make sure we free the data before setting the pending flag to 0 */ - smp_wmb(); - entry->rcu_pending = 0; + struct tp_probes *p = kmalloc(count * sizeof(void *) + + sizeof(struct tp_probes), GFP_KERNEL); + return p == NULL ? NULL : p->probes; } -static void tracepoint_entry_free_old(struct tracepoint_entry *entry, void *old) +static void rcu_free_old_probes(struct rcu_head *head) { - if (!old) - return; - entry->oldptr = old; - entry->rcu_pending = 1; - /* write rcu_pending before calling the RCU callback */ - smp_wmb(); - call_rcu_sched(&entry->rcu, free_old_closure); + kfree(container_of(head, struct tp_probes, u.rcu)); +} + +static inline void release_probes(void *old) +{ + if (old) { + struct tp_probes *tp_probes = container_of(old, + struct tp_probes, probes[0]); + call_rcu_sched(&tp_probes->u.rcu, rcu_free_old_probes); + } } static void debug_print_probes(struct tracepoint_entry *entry) { int i; - if (!tracepoint_debug) + if (!tracepoint_debug || !entry->funcs) return; for (i = 0; entry->funcs[i]; i++) @@ -111,12 +115,13 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe) return ERR_PTR(-EEXIST); } /* + 2 : one for new probe, one for NULL func */ - new = kzalloc((nr_probes + 2) * sizeof(void *), GFP_KERNEL); + new = allocate_probes(nr_probes + 2); if (new == NULL) return ERR_PTR(-ENOMEM); if (old) memcpy(new, old, nr_probes * sizeof(void *)); new[nr_probes] = probe; + new[nr_probes + 1] = NULL; entry->refcount = nr_probes + 1; entry->funcs = new; debug_print_probes(entry); @@ -132,7 +137,7 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe) old = entry->funcs; if (!old) - return NULL; + return ERR_PTR(-ENOENT); debug_print_probes(entry); /* (N -> M), (N > 1, M >= 0) probes */ @@ -151,13 +156,13 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe) int j = 0; /* N -> M, (N > 1, M > 0) */ /* + 1 for NULL */ - new = kzalloc((nr_probes - nr_del + 1) - * sizeof(void *), GFP_KERNEL); + new = allocate_probes(nr_probes - nr_del + 1); if (new == NULL) return ERR_PTR(-ENOMEM); for (i = 0; old[i]; i++) if ((probe && old[i] != probe)) new[j++] = old[i]; + new[nr_probes - nr_del] = NULL; entry->refcount = nr_probes - nr_del; entry->funcs = new; } @@ -215,7 +220,6 @@ static struct tracepoint_entry *add_tracepoint(const char *name) memcpy(&e->name[0], name, name_len); e->funcs = NULL; e->refcount = 0; - e->rcu_pending = 0; hlist_add_head(&e->hlist, head); return e; } @@ -224,32 +228,10 @@ static struct tracepoint_entry *add_tracepoint(const char *name) * Remove the tracepoint from the tracepoint hash table. Must be called with * mutex_lock held. */ -static int remove_tracepoint(const char *name) +static inline void remove_tracepoint(struct tracepoint_entry *e) { - struct hlist_head *head; - struct hlist_node *node; - struct tracepoint_entry *e; - int found = 0; - size_t len = strlen(name) + 1; - u32 hash = jhash(name, len-1, 0); - - head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)]; - hlist_for_each_entry(e, node, head, hlist) { - if (!strcmp(name, e->name)) { - found = 1; - break; - } - } - if (!found) - return -ENOENT; - if (e->refcount) - return -EBUSY; hlist_del(&e->hlist); - /* Make sure the call_rcu_sched has been executed */ - if (e->rcu_pending) - rcu_barrier_sched(); kfree(e); - return 0; } /* @@ -280,6 +262,7 @@ static void set_tracepoint(struct tracepoint_entry **entry, static void disable_tracepoint(struct tracepoint *elem) { elem->state = 0; + rcu_assign_pointer(elem->funcs, NULL); } /** @@ -320,6 +303,23 @@ static void tracepoint_update_probes(void) module_update_tracepoints(); } +static void *tracepoint_add_probe(const char *name, void *probe) +{ + struct tracepoint_entry *entry; + void *old; + + entry = get_tracepoint(name); + if (!entry) { + entry = add_tracepoint(name); + if (IS_ERR(entry)) + return entry; + } + old = tracepoint_entry_add_probe(entry, probe); + if (IS_ERR(old) && !entry->refcount) + remove_tracepoint(entry); + return old; +} + /** * tracepoint_probe_register - Connect a probe to a tracepoint * @name: tracepoint name @@ -330,44 +330,36 @@ static void tracepoint_update_probes(void) */ int tracepoint_probe_register(const char *name, void *probe) { - struct tracepoint_entry *entry; - int ret = 0; void *old; mutex_lock(&tracepoints_mutex); - entry = get_tracepoint(name); - if (!entry) { - entry = add_tracepoint(name); - if (IS_ERR(entry)) { - ret = PTR_ERR(entry); - goto end; - } - } - /* - * If we detect that a call_rcu_sched is pending for this tracepoint, - * make sure it's executed now. - */ - if (entry->rcu_pending) - rcu_barrier_sched(); - old = tracepoint_entry_add_probe(entry, probe); - if (IS_ERR(old)) { - ret = PTR_ERR(old); - goto end; - } + old = tracepoint_add_probe(name, probe); mutex_unlock(&tracepoints_mutex); + if (IS_ERR(old)) + return PTR_ERR(old); + tracepoint_update_probes(); /* may update entry */ - mutex_lock(&tracepoints_mutex); - entry = get_tracepoint(name); - WARN_ON(!entry); - if (entry->rcu_pending) - rcu_barrier_sched(); - tracepoint_entry_free_old(entry, old); -end: - mutex_unlock(&tracepoints_mutex); - return ret; + release_probes(old); + return 0; } EXPORT_SYMBOL_GPL(tracepoint_probe_register); +static void *tracepoint_remove_probe(const char *name, void *probe) +{ + struct tracepoint_entry *entry; + void *old; + + entry = get_tracepoint(name); + if (!entry) + return ERR_PTR(-ENOENT); + old = tracepoint_entry_remove_probe(entry, probe); + if (IS_ERR(old)) + return old; + if (!entry->refcount) + remove_tracepoint(entry); + return old; +} + /** * tracepoint_probe_unregister - Disconnect a probe from a tracepoint * @name: tracepoint name @@ -380,38 +372,104 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register); */ int tracepoint_probe_unregister(const char *name, void *probe) { - struct tracepoint_entry *entry; void *old; - int ret = -ENOENT; mutex_lock(&tracepoints_mutex); - entry = get_tracepoint(name); - if (!entry) - goto end; - if (entry->rcu_pending) - rcu_barrier_sched(); - old = tracepoint_entry_remove_probe(entry, probe); - if (!old) { - printk(KERN_WARNING "Warning: Trying to unregister a probe" - "that doesn't exist\n"); - goto end; - } + old = tracepoint_remove_probe(name, probe); mutex_unlock(&tracepoints_mutex); + if (IS_ERR(old)) + return PTR_ERR(old); + tracepoint_update_probes(); /* may update entry */ + release_probes(old); + return 0; +} +EXPORT_SYMBOL_GPL(tracepoint_probe_unregister); + +static LIST_HEAD(old_probes); +static int need_update; + +static void tracepoint_add_old_probes(void *old) +{ + need_update = 1; + if (old) { + struct tp_probes *tp_probes = container_of(old, + struct tp_probes, probes[0]); + list_add(&tp_probes->u.list, &old_probes); + } +} + +/** + * tracepoint_probe_register_noupdate - register a probe but not connect + * @name: tracepoint name + * @probe: probe handler + * + * caller must call tracepoint_probe_update_all() + */ +int tracepoint_probe_register_noupdate(const char *name, void *probe) +{ + void *old; + mutex_lock(&tracepoints_mutex); - entry = get_tracepoint(name); - if (!entry) - goto end; - if (entry->rcu_pending) - rcu_barrier_sched(); - tracepoint_entry_free_old(entry, old); - remove_tracepoint(name); /* Ignore busy error message */ - ret = 0; -end: + old = tracepoint_add_probe(name, probe); + if (IS_ERR(old)) { + mutex_unlock(&tracepoints_mutex); + return PTR_ERR(old); + } + tracepoint_add_old_probes(old); mutex_unlock(&tracepoints_mutex); - return ret; + return 0; } -EXPORT_SYMBOL_GPL(tracepoint_probe_unregister); +EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate); + +/** + * tracepoint_probe_unregister_noupdate - remove a probe but not disconnect + * @name: tracepoint name + * @probe: probe function pointer + * + * caller must call tracepoint_probe_update_all() + */ +int tracepoint_probe_unregister_noupdate(const char *name, void *probe) +{ + void *old; + + mutex_lock(&tracepoints_mutex); + old = tracepoint_remove_probe(name, probe); + if (IS_ERR(old)) { + mutex_unlock(&tracepoints_mutex); + return PTR_ERR(old); + } + tracepoint_add_old_probes(old); + mutex_unlock(&tracepoints_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(tracepoint_probe_unregister_noupdate); + +/** + * tracepoint_probe_update_all - update tracepoints + */ +void tracepoint_probe_update_all(void) +{ + LIST_HEAD(release_probes); + struct tp_probes *pos, *next; + + mutex_lock(&tracepoints_mutex); + if (!need_update) { + mutex_unlock(&tracepoints_mutex); + return; + } + if (!list_empty(&old_probes)) + list_replace_init(&old_probes, &release_probes); + need_update = 0; + mutex_unlock(&tracepoints_mutex); + + tracepoint_update_probes(); + list_for_each_entry_safe(pos, next, &release_probes, u.list) { + list_del(&pos->u.list); + call_rcu_sched(&pos->u.rcu, rcu_free_old_probes); + } +} +EXPORT_SYMBOL_GPL(tracepoint_probe_update_all); /** * tracepoint_get_iter_range - Get a next tracepoint iterator given a range. @@ -483,3 +541,36 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter) iter->tracepoint = NULL; } EXPORT_SYMBOL_GPL(tracepoint_iter_reset); + +#ifdef CONFIG_MODULES + +int tracepoint_module_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + switch (val) { + case MODULE_STATE_COMING: + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + break; + case MODULE_STATE_GOING: + tracepoint_update_probe_range(mod->tracepoints, + mod->tracepoints + mod->num_tracepoints); + break; + } + return 0; +} + +struct notifier_block tracepoint_module_nb = { + .notifier_call = tracepoint_module_notify, + .priority = 0, +}; + +static int init_tracepoints(void) +{ + return register_module_notifier(&tracepoint_module_nb); +} +__initcall(init_tracepoints); + +#endif /* CONFIG_MODULES */ diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 8ebcd85..43f891b 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -27,6 +27,7 @@ */ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) { + const struct cred *tcred; struct timespec uptime, ts; u64 ac_etime; @@ -53,10 +54,11 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) stats->ac_flag |= AXSIG; stats->ac_nice = task_nice(tsk); stats->ac_sched = tsk->policy; - stats->ac_uid = tsk->uid; - stats->ac_gid = tsk->gid; stats->ac_pid = tsk->pid; rcu_read_lock(); + tcred = __task_cred(tsk); + stats->ac_uid = tcred->uid; + stats->ac_gid = tcred->gid; stats->ac_ppid = pid_alive(tsk) ? rcu_dereference(tsk->real_parent)->tgid : 0; rcu_read_unlock(); @@ -90,8 +92,8 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) mm = get_task_mm(p); if (mm) { /* adjust to KB unit */ - stats->hiwater_rss = mm->hiwater_rss * PAGE_SIZE / KB; - stats->hiwater_vm = mm->hiwater_vm * PAGE_SIZE / KB; + stats->hiwater_rss = get_mm_hiwater_rss(mm) * PAGE_SIZE / KB; + stats->hiwater_vm = get_mm_hiwater_vm(mm) * PAGE_SIZE / KB; mmput(mm); } stats->read_char = p->ioac.rchar; diff --git a/kernel/uid16.c b/kernel/uid16.c index 3e41c16..2460c31 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -84,11 +84,12 @@ asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid) asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid, old_uid_t __user *suid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(high2lowuid(current->uid), ruid)) && - !(retval = put_user(high2lowuid(current->euid), euid))) - retval = put_user(high2lowuid(current->suid), suid); + if (!(retval = put_user(high2lowuid(cred->uid), ruid)) && + !(retval = put_user(high2lowuid(cred->euid), euid))) + retval = put_user(high2lowuid(cred->suid), suid); return retval; } @@ -104,11 +105,12 @@ asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid) asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid, old_gid_t __user *sgid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(high2lowgid(current->gid), rgid)) && - !(retval = put_user(high2lowgid(current->egid), egid))) - retval = put_user(high2lowgid(current->sgid), sgid); + if (!(retval = put_user(high2lowgid(cred->gid), rgid)) && + !(retval = put_user(high2lowgid(cred->egid), egid))) + retval = put_user(high2lowgid(cred->sgid), sgid); return retval; } @@ -161,25 +163,24 @@ static int groups16_from_user(struct group_info *group_info, asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist) { - int i = 0; + const struct cred *cred = current_cred(); + int i; if (gidsetsize < 0) return -EINVAL; - get_group_info(current->group_info); - i = current->group_info->ngroups; + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups16_to_user(grouplist, current->group_info)) { + if (groups16_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: - put_group_info(current->group_info); return i; } @@ -210,20 +211,20 @@ asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist) asmlinkage long sys_getuid16(void) { - return high2lowuid(current->uid); + return high2lowuid(current_uid()); } asmlinkage long sys_geteuid16(void) { - return high2lowuid(current->euid); + return high2lowuid(current_euid()); } asmlinkage long sys_getgid16(void) { - return high2lowgid(current->gid); + return high2lowgid(current_gid()); } asmlinkage long sys_getegid16(void) { - return high2lowgid(current->egid); + return high2lowgid(current_egid()); } diff --git a/kernel/user.c b/kernel/user.c index 39d6159..477b666 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -16,12 +16,13 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/user_namespace.h> +#include "cred-internals.h" struct user_namespace init_user_ns = { .kref = { - .refcount = ATOMIC_INIT(2), + .refcount = ATOMIC_INIT(1), }, - .root_user = &root_user, + .creator = &root_user, }; EXPORT_SYMBOL_GPL(init_user_ns); @@ -47,12 +48,14 @@ static struct kmem_cache *uid_cachep; */ static DEFINE_SPINLOCK(uidhash_lock); +/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->creator */ struct user_struct root_user = { - .__count = ATOMIC_INIT(1), + .__count = ATOMIC_INIT(2), .processes = ATOMIC_INIT(1), .files = ATOMIC_INIT(0), .sigpending = ATOMIC_INIT(0), .locked_shm = 0, + .user_ns = &init_user_ns, #ifdef CONFIG_USER_SCHED .tg = &init_task_group, #endif @@ -101,19 +104,15 @@ static int sched_create_user(struct user_struct *up) if (IS_ERR(up->tg)) rc = -ENOMEM; - return rc; -} + set_tg_uid(up); -static void sched_switch_user(struct task_struct *p) -{ - sched_move_task(p); + return rc; } #else /* CONFIG_USER_SCHED */ static void sched_destroy_user(struct user_struct *up) { } static int sched_create_user(struct user_struct *up) { return 0; } -static void sched_switch_user(struct task_struct *p) { } #endif /* CONFIG_USER_SCHED */ @@ -242,13 +241,21 @@ static struct kobj_type uids_ktype = { .release = uids_release, }; -/* create /sys/kernel/uids/<uid>/cpu_share file for this user */ +/* + * Create /sys/kernel/uids/<uid>/cpu_share file for this user + * We do not create this file for users in a user namespace (until + * sysfs tagging is implemented). + * + * See Documentation/scheduler/sched-design-CFS.txt for ramifications. + */ static int uids_user_create(struct user_struct *up) { struct kobject *kobj = &up->kobj; int error; memset(kobj, 0, sizeof(struct kobject)); + if (up->user_ns != &init_user_ns) + return 0; kobj->kset = uids_kset; error = kobject_init_and_add(kobj, &uids_ktype, NULL, "%d", up->uid); if (error) { @@ -284,6 +291,8 @@ static void remove_user_sysfs_dir(struct work_struct *w) unsigned long flags; int remove_user = 0; + if (up->user_ns != &init_user_ns) + return; /* Make uid_hash_remove() + sysfs_remove_file() + kobject_del() * atomic. */ @@ -319,12 +328,13 @@ done: * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ -static inline void free_user(struct user_struct *up, unsigned long flags) +static void free_user(struct user_struct *up, unsigned long flags) { /* restore back the count */ atomic_inc(&up->__count); spin_unlock_irqrestore(&uidhash_lock, flags); + put_user_ns(up->user_ns); INIT_WORK(&up->work, remove_user_sysfs_dir); schedule_work(&up->work); } @@ -340,13 +350,14 @@ static inline void uids_mutex_unlock(void) { } * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ -static inline void free_user(struct user_struct *up, unsigned long flags) +static void free_user(struct user_struct *up, unsigned long flags) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); sched_destroy_user(up); key_put(up->uid_keyring); key_put(up->session_keyring); + put_user_ns(up->user_ns); kmem_cache_free(uid_cachep, up); } @@ -362,7 +373,7 @@ struct user_struct *find_user(uid_t uid) { struct user_struct *ret; unsigned long flags; - struct user_namespace *ns = current->nsproxy->user_ns; + struct user_namespace *ns = current_user_ns(); spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(ns, uid)); @@ -409,6 +420,8 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) if (sched_create_user(new) < 0) goto out_free_user; + new->user_ns = get_user_ns(ns); + if (uids_user_create(new)) goto out_destoy_sched; @@ -432,7 +445,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) up = new; } spin_unlock_irq(&uidhash_lock); - } uids_mutex_unlock(); @@ -441,6 +453,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) out_destoy_sched: sched_destroy_user(new); + put_user_ns(new->user_ns); out_free_user: kmem_cache_free(uid_cachep, new); out_unlock: @@ -448,63 +461,6 @@ out_unlock: return NULL; } -void switch_uid(struct user_struct *new_user) -{ - struct user_struct *old_user; - - /* What if a process setreuid()'s and this brings the - * new uid over his NPROC rlimit? We can check this now - * cheaply with the new uid cache, so if it matters - * we should be checking for it. -DaveM - */ - old_user = current->user; - atomic_inc(&new_user->processes); - atomic_dec(&old_user->processes); - switch_uid_keyring(new_user); - current->user = new_user; - sched_switch_user(current); - - /* - * We need to synchronize with __sigqueue_alloc() - * doing a get_uid(p->user).. If that saw the old - * user value, we need to wait until it has exited - * its critical region before we can free the old - * structure. - */ - smp_mb(); - spin_unlock_wait(¤t->sighand->siglock); - - free_uid(old_user); - suid_keys(current); -} - -#ifdef CONFIG_USER_NS -void release_uids(struct user_namespace *ns) -{ - int i; - unsigned long flags; - struct hlist_head *head; - struct hlist_node *nd; - - spin_lock_irqsave(&uidhash_lock, flags); - /* - * collapse the chains so that the user_struct-s will - * be still alive, but not in hashes. subsequent free_uid() - * will free them. - */ - for (i = 0; i < UIDHASH_SZ; i++) { - head = ns->uidhash_table + i; - while (!hlist_empty(head)) { - nd = head->first; - hlist_del_init(nd); - } - } - spin_unlock_irqrestore(&uidhash_lock, flags); - - free_uid(ns->root_user); -} -#endif - static int __init uid_cache_init(void) { int n; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 532858f..7908431 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -9,60 +9,55 @@ #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/user_namespace.h> +#include <linux/cred.h> /* - * Clone a new ns copying an original user ns, setting refcount to 1 - * @old_ns: namespace to clone - * Return NULL on error (failure to kmalloc), new ns otherwise + * Create a new user namespace, deriving the creator from the user in the + * passed credentials, and replacing that user with the new root user for the + * new namespace. + * + * This is called by copy_creds(), which will finish setting the target task's + * credentials. */ -static struct user_namespace *clone_user_ns(struct user_namespace *old_ns) +int create_user_ns(struct cred *new) { struct user_namespace *ns; - struct user_struct *new_user; + struct user_struct *root_user; int n; ns = kmalloc(sizeof(struct user_namespace), GFP_KERNEL); if (!ns) - return ERR_PTR(-ENOMEM); + return -ENOMEM; kref_init(&ns->kref); for (n = 0; n < UIDHASH_SZ; ++n) INIT_HLIST_HEAD(ns->uidhash_table + n); - /* Insert new root user. */ - ns->root_user = alloc_uid(ns, 0); - if (!ns->root_user) { + /* Alloc new root user. */ + root_user = alloc_uid(ns, 0); + if (!root_user) { kfree(ns); - return ERR_PTR(-ENOMEM); + return -ENOMEM; } - /* Reset current->user with a new one */ - new_user = alloc_uid(ns, current->uid); - if (!new_user) { - free_uid(ns->root_user); - kfree(ns); - return ERR_PTR(-ENOMEM); - } - - switch_uid(new_user); - return ns; -} - -struct user_namespace * copy_user_ns(int flags, struct user_namespace *old_ns) -{ - struct user_namespace *new_ns; - - BUG_ON(!old_ns); - get_user_ns(old_ns); - - if (!(flags & CLONE_NEWUSER)) - return old_ns; + /* set the new root user in the credentials under preparation */ + ns->creator = new->user; + new->user = root_user; + new->uid = new->euid = new->suid = new->fsuid = 0; + new->gid = new->egid = new->sgid = new->fsgid = 0; + put_group_info(new->group_info); + new->group_info = get_group_info(&init_groups); +#ifdef CONFIG_KEYS + key_put(new->request_key_auth); + new->request_key_auth = NULL; +#endif + /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ - new_ns = clone_user_ns(old_ns); + /* alloc_uid() incremented the userns refcount. Just set it to 1 */ + kref_set(&ns->kref, 1); - put_user_ns(old_ns); - return new_ns; + return 0; } void free_user_ns(struct kref *kref) @@ -70,7 +65,7 @@ void free_user_ns(struct kref *kref) struct user_namespace *ns; ns = container_of(kref, struct user_namespace, kref); - release_uids(ns); + free_uid(ns->creator); kfree(ns); } EXPORT_SYMBOL(free_user_ns); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index d4dc69d..2f44583 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -73,7 +73,7 @@ static DEFINE_SPINLOCK(workqueue_lock); static LIST_HEAD(workqueues); static int singlethread_cpu __read_mostly; -static cpumask_t cpu_singlethread_map __read_mostly; +static const struct cpumask *cpu_singlethread_map __read_mostly; /* * _cpu_down() first removes CPU from cpu_online_map, then CPU_DEAD * flushes cwq->worklist. This means that flush_workqueue/wait_on_work @@ -81,24 +81,24 @@ static cpumask_t cpu_singlethread_map __read_mostly; * use cpu_possible_map, the cpumask below is more a documentation * than optimization. */ -static cpumask_t cpu_populated_map __read_mostly; +static cpumask_var_t cpu_populated_map __read_mostly; /* If it's single threaded, it isn't in the list of workqueues. */ -static inline int is_single_threaded(struct workqueue_struct *wq) +static inline int is_wq_single_threaded(struct workqueue_struct *wq) { return wq->singlethread; } -static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq) +static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq) { - return is_single_threaded(wq) - ? &cpu_singlethread_map : &cpu_populated_map; + return is_wq_single_threaded(wq) + ? cpu_singlethread_map : cpu_populated_map; } static struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu) { - if (unlikely(is_single_threaded(wq))) + if (unlikely(is_wq_single_threaded(wq))) cpu = singlethread_cpu; return per_cpu_ptr(wq->cpu_wq, cpu); } @@ -410,7 +410,7 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq) */ void flush_workqueue(struct workqueue_struct *wq) { - const cpumask_t *cpu_map = wq_cpu_map(wq); + const struct cpumask *cpu_map = wq_cpu_map(wq); int cpu; might_sleep(); @@ -532,7 +532,7 @@ static void wait_on_work(struct work_struct *work) { struct cpu_workqueue_struct *cwq; struct workqueue_struct *wq; - const cpumask_t *cpu_map; + const struct cpumask *cpu_map; int cpu; might_sleep(); @@ -769,7 +769,7 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; struct workqueue_struct *wq = cwq->wq; - const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d"; + const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d"; struct task_struct *p; p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu); @@ -903,7 +903,7 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq) */ void destroy_workqueue(struct workqueue_struct *wq) { - const cpumask_t *cpu_map = wq_cpu_map(wq); + const struct cpumask *cpu_map = wq_cpu_map(wq); int cpu; cpu_maps_update_begin(); @@ -933,7 +933,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb, switch (action) { case CPU_UP_PREPARE: - cpu_set(cpu, cpu_populated_map); + cpumask_set_cpu(cpu, cpu_populated_map); } undo: list_for_each_entry(wq, &workqueues, list) { @@ -964,7 +964,7 @@ undo: switch (action) { case CPU_UP_CANCELED: case CPU_POST_DEAD: - cpu_clear(cpu, cpu_populated_map); + cpumask_clear_cpu(cpu, cpu_populated_map); } return ret; @@ -1017,9 +1017,11 @@ EXPORT_SYMBOL_GPL(work_on_cpu); void __init init_workqueues(void) { - cpu_populated_map = cpu_online_map; - singlethread_cpu = first_cpu(cpu_possible_map); - cpu_singlethread_map = cpumask_of_cpu(singlethread_cpu); + alloc_cpumask_var(&cpu_populated_map, GFP_KERNEL); + + cpumask_copy(cpu_populated_map, cpu_online_mask); + singlethread_cpu = cpumask_first(cpu_possible_mask); + cpu_singlethread_map = cpumask_of(singlethread_cpu); hotcpu_notifier(workqueue_cpu_callback, 0); keventd_wq = create_workqueue("events"); BUG_ON(!keventd_wq); |