summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile12
-rw-r--r--kernel/acct.c2
-rw-r--r--kernel/async.c20
-rw-r--r--kernel/audit.c38
-rw-r--r--kernel/audit_watch.c24
-rw-r--r--kernel/auditfilter.c2
-rw-r--r--kernel/auditsc.c29
-rw-r--r--kernel/bounds.c4
-rw-r--r--kernel/bpf/arraymap.c43
-rw-r--r--kernel/bpf/core.c101
-rw-r--r--kernel/bpf/hashtab.c9
-rw-r--r--kernel/bpf/syscall.c89
-rw-r--r--kernel/bpf/verifier.c415
-rw-r--r--kernel/capability.c36
-rw-r--r--kernel/cgroup.c149
-rw-r--r--kernel/configs/android-base.config160
-rw-r--r--kernel/configs/android-recommended.config125
-rw-r--r--kernel/cpu.c77
-rw-r--r--kernel/cpuset.c55
-rw-r--r--kernel/debug/debug_core.c4
-rw-r--r--kernel/debug/kdb/kdb_bp.c4
-rw-r--r--kernel/debug/kdb/kdb_io.c27
-rw-r--r--kernel/debug/kdb/kdb_main.c27
-rw-r--r--kernel/debug/kdb/kdb_private.h2
-rw-r--r--kernel/debug/kdb/kdb_support.c14
-rw-r--r--kernel/events/callchain.c10
-rw-r--r--kernel/events/core.c206
-rw-r--r--kernel/events/hw_breakpoint.c30
-rw-r--r--kernel/events/ring_buffer.c57
-rw-r--r--kernel/events/uprobes.c16
-rw-r--r--kernel/exit.c25
-rw-r--r--kernel/extable.c2
-rw-r--r--kernel/fork.c183
-rw-r--r--kernel/futex.c184
-rw-r--r--kernel/gcov/Kconfig1
-rw-r--r--kernel/gcov/base.c6
-rw-r--r--kernel/gcov/gcc_4_7.c4
-rw-r--r--kernel/groups.c5
-rw-r--r--kernel/hung_task.c8
-rw-r--r--kernel/irq/chip.c14
-rw-r--r--kernel/irq/generic-chip.c21
-rw-r--r--kernel/irq/manage.c27
-rw-r--r--kernel/jump_label.c9
-rw-r--r--kernel/kcov.c431
-rw-r--r--kernel/kprobes.c33
-rw-r--r--kernel/kthread.c115
-rw-r--r--kernel/locking/Makefile3
-rw-r--r--kernel/locking/lockdep.c27
-rw-r--r--kernel/locking/locktorture.c4
-rw-r--r--kernel/locking/mutex-debug.c12
-rw-r--r--kernel/locking/mutex-debug.h4
-rw-r--r--kernel/locking/mutex.c11
-rw-r--r--kernel/locking/mutex.h2
-rw-r--r--kernel/locking/osq_lock.c13
-rw-r--r--kernel/locking/percpu-rwsem.c229
-rw-r--r--kernel/locking/qspinlock.c8
-rw-r--r--kernel/locking/rtmutex.c120
-rw-r--r--kernel/locking/rtmutex_common.h13
-rw-r--r--kernel/locking/rwsem-xadd.c27
-rw-r--r--kernel/membarrier.c4
-rw-r--r--kernel/memremap.c15
-rw-r--r--kernel/module.c43
-rw-r--r--kernel/padata.c7
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/pid.c15
-rw-r--r--kernel/pid_namespace.c2
-rw-r--r--kernel/power/Kconfig11
-rw-r--r--kernel/power/Makefile2
-rw-r--r--kernel/power/hibernate.c20
-rw-r--r--kernel/power/main.c11
-rw-r--r--kernel/power/power.h5
-rw-r--r--kernel/power/process.c27
-rw-r--r--kernel/power/suspend.c45
-rw-r--r--kernel/power/suspend_test.c4
-rw-r--r--kernel/power/swap.c18
-rw-r--r--kernel/power/user.c19
-rw-r--r--kernel/power/wakeup_reason.c225
-rw-r--r--kernel/printk/braille.c15
-rw-r--r--kernel/printk/braille.h13
-rw-r--r--kernel/printk/printk.c22
-rw-r--r--kernel/profile.c4
-rw-r--r--kernel/ptrace.c70
-rw-r--r--kernel/rcu/Makefile4
-rw-r--r--kernel/rcu/sync.c13
-rw-r--r--kernel/rcu/tree.c34
-rw-r--r--kernel/rcu/tree_plugin.h1
-rw-r--r--kernel/relay.c2
-rw-r--r--kernel/resource.c16
-rw-r--r--kernel/sched/Makefile10
-rw-r--r--kernel/sched/auto_group.c23
-rw-r--r--kernel/sched/core.c607
-rw-r--r--kernel/sched/cpufreq.c63
-rw-r--r--kernel/sched/cpufreq_schedutil.c827
-rw-r--r--kernel/sched/cputime.c23
-rw-r--r--kernel/sched/deadline.c200
-rw-r--r--kernel/sched/debug.c26
-rw-r--r--kernel/sched/energy.c124
-rw-r--r--kernel/sched/fair.c2826
-rw-r--r--kernel/sched/features.h9
-rw-r--r--kernel/sched/idle.c6
-rw-r--r--kernel/sched/idle_task.c3
-rw-r--r--kernel/sched/loadavg.c4
-rw-r--r--kernel/sched/rt.c477
-rw-r--r--kernel/sched/sched.h334
-rw-r--r--kernel/sched/stats.c26
-rw-r--r--kernel/sched/stop_task.c6
-rw-r--r--kernel/sched/tune.c955
-rw-r--r--kernel/sched/tune.h55
-rw-r--r--kernel/sched/walt.c900
-rw-r--r--kernel/sched/walt.h64
-rw-r--r--kernel/seccomp.c192
-rw-r--r--kernel/signal.c116
-rw-r--r--kernel/softirq.c2
-rw-r--r--kernel/sys.c297
-rw-r--r--kernel/sysctl.c143
-rw-r--r--kernel/time/alarmtimer.c18
-rw-r--r--kernel/time/hrtimer.c21
-rw-r--r--kernel/time/posix-clock.c34
-rw-r--r--kernel/time/posix-cpu-timers.c2
-rw-r--r--kernel/time/posix-timers.c63
-rw-r--r--kernel/time/sched_clock.c5
-rw-r--r--kernel/time/tick-broadcast.c11
-rw-r--r--kernel/time/tick-sched.c31
-rw-r--r--kernel/time/time.c6
-rw-r--r--kernel/time/timekeeping.c165
-rw-r--r--kernel/time/timer.c15
-rw-r--r--kernel/time/timer_list.c8
-rw-r--r--kernel/time/timer_stats.c2
-rw-r--r--kernel/trace/Kconfig14
-rw-r--r--kernel/trace/Makefile2
-rw-r--r--kernel/trace/blktrace.c36
-rw-r--r--kernel/trace/bpf_trace.c8
-rw-r--r--kernel/trace/ftrace.c54
-rw-r--r--kernel/trace/gpu-traces.c23
-rw-r--r--kernel/trace/ring_buffer.c55
-rw-r--r--kernel/trace/trace.c277
-rw-r--r--kernel/trace/trace.h4
-rw-r--r--kernel/trace/trace_events.c16
-rw-r--r--kernel/trace/trace_events_filter.c7
-rw-r--r--kernel/trace/trace_events_trigger.c29
-rw-r--r--kernel/trace/trace_functions_graph.c66
-rw-r--r--kernel/trace/trace_irqsoff.c133
-rw-r--r--kernel/trace/trace_kdb.c6
-rw-r--r--kernel/trace/trace_kprobe.c45
-rw-r--r--kernel/trace/trace_output.c184
-rw-r--r--kernel/trace/trace_probe.c8
-rw-r--r--kernel/trace/trace_probe.h2
-rw-r--r--kernel/trace/trace_selftest.c2
-rw-r--r--kernel/trace/trace_uprobe.c11
-rw-r--r--kernel/tracepoint.c4
-rw-r--r--kernel/uid16.c1
-rw-r--r--kernel/user.c3
-rw-r--r--kernel/user_namespace.c39
-rw-r--r--kernel/utsname_sysctl.c41
-rw-r--r--kernel/watchdog.c126
-rw-r--r--kernel/workqueue.c79
-rw-r--r--kernel/workqueue_internal.h3
157 files changed, 12011 insertions, 1963 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 53abf008ecb3..2dea801370f2 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -19,6 +19,17 @@ CFLAGS_REMOVE_cgroup-debug.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_irq_work.o = $(CC_FLAGS_FTRACE)
endif
+# Prevents flicker of uninteresting __do_softirq()/__local_bh_disable_ip()
+# in coverage traces.
+KCOV_INSTRUMENT_softirq.o := n
+# These are called from save_stack_trace() on slub debug path,
+# and produce insane amounts of uninteresting coverage.
+KCOV_INSTRUMENT_module.o := n
+KCOV_INSTRUMENT_extable.o := n
+# Don't self-instrument.
+KCOV_INSTRUMENT_kcov.o := n
+KASAN_SANITIZE_kcov.o := n
+
# cond_syscall is currently not LTO compatible
CFLAGS_sys_ni.o = $(DISABLE_LTO)
@@ -69,6 +80,7 @@ obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o audit_fsnotify.o
obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
obj-$(CONFIG_GCOV_KERNEL) += gcov/
+obj-$(CONFIG_KCOV) += kcov.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += debug/
obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
diff --git a/kernel/acct.c b/kernel/acct.c
index 74963d192c5d..37f1dc696fbd 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -99,7 +99,7 @@ static int check_free_space(struct bsd_acct_struct *acct)
{
struct kstatfs sbuf;
- if (time_is_before_jiffies(acct->needcheck))
+ if (time_is_after_jiffies(acct->needcheck))
goto out;
/* May block */
diff --git a/kernel/async.c b/kernel/async.c
index 4c3773c0bf63..f1fd155abff6 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -84,20 +84,24 @@ static atomic_t entry_count;
static async_cookie_t lowest_in_progress(struct async_domain *domain)
{
- struct list_head *pending;
+ struct async_entry *first = NULL;
async_cookie_t ret = ASYNC_COOKIE_MAX;
unsigned long flags;
spin_lock_irqsave(&async_lock, flags);
- if (domain)
- pending = &domain->pending;
- else
- pending = &async_global_pending;
+ if (domain) {
+ if (!list_empty(&domain->pending))
+ first = list_first_entry(&domain->pending,
+ struct async_entry, domain_list);
+ } else {
+ if (!list_empty(&async_global_pending))
+ first = list_first_entry(&async_global_pending,
+ struct async_entry, global_list);
+ }
- if (!list_empty(pending))
- ret = list_first_entry(pending, struct async_entry,
- domain_list)->cookie;
+ if (first)
+ ret = first->cookie;
spin_unlock_irqrestore(&async_lock, flags);
return ret;
diff --git a/kernel/audit.c b/kernel/audit.c
index 5ffcbd354a52..d440c25cb3be 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -64,7 +64,6 @@
#include <linux/security.h>
#endif
#include <linux/freezer.h>
-#include <linux/tty.h>
#include <linux/pid_namespace.h>
#include <net/netns/generic.h>
@@ -80,13 +79,13 @@ static int audit_initialized;
#define AUDIT_OFF 0
#define AUDIT_ON 1
#define AUDIT_LOCKED 2
-u32 audit_enabled;
-u32 audit_ever_enabled;
+u32 audit_enabled = AUDIT_OFF;
+u32 audit_ever_enabled = !!AUDIT_OFF;
EXPORT_SYMBOL_GPL(audit_enabled);
/* Default state when kernel boots without any parameters. */
-static u32 audit_default;
+static u32 audit_default = AUDIT_OFF;
/* If auditing cannot proceed, audit_failure selects what happens. */
static u32 audit_failure = AUDIT_FAIL_PRINTK;
@@ -745,6 +744,8 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature
return;
ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE);
+ if (!ab)
+ return;
audit_log_task_info(ab, current);
audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d",
audit_feature_names[which], !!old_feature, !!new_feature,
@@ -870,6 +871,12 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
return err;
}
if (s.mask & AUDIT_STATUS_PID) {
+ /* NOTE: we are using task_tgid_vnr() below because
+ * the s.pid value is relative to the namespace
+ * of the caller; at present this doesn't matter
+ * much since you can really only run auditd
+ * from the initial pid namespace, but something
+ * to keep in mind if this changes */
int new_pid = s.pid;
if ((!new_pid) && (task_tgid_vnr(current) != audit_pid))
@@ -1179,8 +1186,6 @@ static int __init audit_init(void)
skb_queue_head_init(&audit_skb_queue);
skb_queue_head_init(&audit_skb_hold_queue);
audit_initialized = AUDIT_INITIALIZED;
- audit_enabled = audit_default;
- audit_ever_enabled |= !!audit_default;
audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "initialized");
@@ -1197,6 +1202,8 @@ static int __init audit_enable(char *str)
audit_default = !!simple_strtol(str, NULL, 0);
if (!audit_default)
audit_initialized = AUDIT_DISABLED;
+ audit_enabled = audit_default;
+ audit_ever_enabled = !!audit_enabled;
pr_info("%s\n", audit_default ?
"enabled (after initialization)" : "disabled (until reboot)");
@@ -1876,27 +1883,20 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
{
const struct cred *cred;
char comm[sizeof(tsk->comm)];
- char *tty;
+ struct tty_struct *tty;
if (!ab)
return;
/* tsk == current */
cred = current_cred();
-
- spin_lock_irq(&tsk->sighand->siglock);
- if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name)
- tty = tsk->signal->tty->name;
- else
- tty = "(none)";
- spin_unlock_irq(&tsk->sighand->siglock);
-
+ tty = audit_get_tty(tsk);
audit_log_format(ab,
" ppid=%d pid=%d auid=%u uid=%u gid=%u"
" euid=%u suid=%u fsuid=%u"
" egid=%u sgid=%u fsgid=%u tty=%s ses=%u",
task_ppid_nr(tsk),
- task_pid_nr(tsk),
+ task_tgid_nr(tsk),
from_kuid(&init_user_ns, audit_get_loginuid(tsk)),
from_kuid(&init_user_ns, cred->uid),
from_kgid(&init_user_ns, cred->gid),
@@ -1906,11 +1906,11 @@ void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk)
from_kgid(&init_user_ns, cred->egid),
from_kgid(&init_user_ns, cred->sgid),
from_kgid(&init_user_ns, cred->fsgid),
- tty, audit_get_sessionid(tsk));
-
+ tty ? tty_name(tty) : "(none)",
+ audit_get_sessionid(tsk));
+ audit_put_tty(tty);
audit_log_format(ab, " comm=");
audit_log_untrustedstring(ab, get_task_comm(comm, tsk));
-
audit_log_d_path_exe(ab, tsk->mm);
audit_log_task_context(ab);
}
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 939945a5649c..f45a9a5d3e47 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -419,6 +419,13 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
struct path parent_path;
int h, ret = 0;
+ /*
+ * When we will be calling audit_add_to_parent, krule->watch might have
+ * been updated and watch might have been freed.
+ * So we need to keep a reference of watch.
+ */
+ audit_get_watch(watch);
+
mutex_unlock(&audit_filter_mutex);
/* Avoid calling path_lookup under audit_filter_mutex. */
@@ -427,8 +434,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
/* caller expects mutex locked */
mutex_lock(&audit_filter_mutex);
- if (ret)
+ if (ret) {
+ audit_put_watch(watch);
return ret;
+ }
/* either find an old parent or attach a new one */
parent = audit_find_parent(d_backing_inode(parent_path.dentry));
@@ -446,6 +455,7 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
*list = &audit_inode_hash[h];
error:
path_put(&parent_path);
+ audit_put_watch(watch);
return ret;
}
@@ -457,13 +467,15 @@ void audit_remove_watch_rule(struct audit_krule *krule)
list_del(&krule->rlist);
if (list_empty(&watch->rules)) {
+ /*
+ * audit_remove_watch() drops our reference to 'parent' which
+ * can get freed. Grab our own reference to be safe.
+ */
+ audit_get_parent(parent);
audit_remove_watch(watch);
-
- if (list_empty(&parent->watches)) {
- audit_get_parent(parent);
+ if (list_empty(&parent->watches))
fsnotify_destroy_mark(&parent->mark, audit_watch_group);
- audit_put_parent(parent);
- }
+ audit_put_parent(parent);
}
}
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index b8ff9e193753..b57f929f1b46 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -406,7 +406,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
return -EINVAL;
break;
case AUDIT_EXE:
- if (f->op != Audit_equal)
+ if (f->op != Audit_not_equal && f->op != Audit_equal)
return -EINVAL;
if (entry->rule.listnr != AUDIT_FILTER_EXIT)
return -EINVAL;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 48f45987dc6c..2b9a4739381d 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -458,7 +458,7 @@ static int audit_filter_rules(struct task_struct *tsk,
switch (f->type) {
case AUDIT_PID:
- pid = task_pid_nr(tsk);
+ pid = task_tgid_nr(tsk);
result = audit_comparator(pid, f->op, f->val);
break;
case AUDIT_PPID:
@@ -470,6 +470,8 @@ static int audit_filter_rules(struct task_struct *tsk,
break;
case AUDIT_EXE:
result = audit_exe_compare(tsk, rule->exe);
+ if (f->op == Audit_not_equal)
+ result = !result;
break;
case AUDIT_UID:
result = audit_uid_comparator(cred->uid, f->op, f->uid);
@@ -1976,21 +1978,26 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
{
struct audit_buffer *ab;
uid_t uid, oldloginuid, loginuid;
+ struct tty_struct *tty;
if (!audit_enabled)
return;
+ ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
+ if (!ab)
+ return;
+
uid = from_kuid(&init_user_ns, task_uid(current));
oldloginuid = from_kuid(&init_user_ns, koldloginuid);
loginuid = from_kuid(&init_user_ns, kloginuid),
+ tty = audit_get_tty(current);
- ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN);
- if (!ab)
- return;
- audit_log_format(ab, "pid=%d uid=%u", task_pid_nr(current), uid);
+ audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid);
audit_log_task_context(ab);
- audit_log_format(ab, " old-auid=%u auid=%u old-ses=%u ses=%u res=%d",
- oldloginuid, loginuid, oldsessionid, sessionid, !rc);
+ audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d",
+ oldloginuid, loginuid, tty ? tty_name(tty) : "(none)",
+ oldsessionid, sessionid, !rc);
+ audit_put_tty(tty);
audit_log_end(ab);
}
@@ -2212,7 +2219,7 @@ void __audit_ptrace(struct task_struct *t)
{
struct audit_context *context = current->audit_context;
- context->target_pid = task_pid_nr(t);
+ context->target_pid = task_tgid_nr(t);
context->target_auid = audit_get_loginuid(t);
context->target_uid = task_uid(t);
context->target_sessionid = audit_get_sessionid(t);
@@ -2237,7 +2244,7 @@ int __audit_signal_info(int sig, struct task_struct *t)
if (audit_pid && t->tgid == audit_pid) {
if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
- audit_sig_pid = task_pid_nr(tsk);
+ audit_sig_pid = task_tgid_nr(tsk);
if (uid_valid(tsk->loginuid))
audit_sig_uid = tsk->loginuid;
else
@@ -2337,7 +2344,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
void __audit_log_capset(const struct cred *new, const struct cred *old)
{
struct audit_context *context = current->audit_context;
- context->capset.pid = task_pid_nr(current);
+ context->capset.pid = task_tgid_nr(current);
context->capset.cap.effective = new->cap_effective;
context->capset.cap.inheritable = new->cap_effective;
context->capset.cap.permitted = new->cap_permitted;
@@ -2369,7 +2376,7 @@ static void audit_log_task(struct audit_buffer *ab)
from_kgid(&init_user_ns, gid),
sessionid);
audit_log_task_context(ab);
- audit_log_format(ab, " pid=%d comm=", task_pid_nr(current));
+ audit_log_format(ab, " pid=%d comm=", task_tgid_nr(current));
audit_log_untrustedstring(ab, get_task_comm(comm, current));
audit_log_d_path_exe(ab, current->mm);
}
diff --git a/kernel/bounds.c b/kernel/bounds.c
index e1d1d1952bfa..c37f68d758db 100644
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -12,7 +12,7 @@
#include <linux/log2.h>
#include <linux/spinlock_types.h>
-void foo(void)
+int main(void)
{
/* The enum constants to put into include/generated/bounds.h */
DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
@@ -22,4 +22,6 @@ void foo(void)
#endif
DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t));
/* End of constants */
+
+ return 0;
}
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index b0799bced518..daa4e0782cf7 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -20,8 +20,10 @@
/* Called from syscall */
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
+ u32 elem_size, array_size, index_mask, max_entries;
+ bool unpriv = !capable(CAP_SYS_ADMIN);
struct bpf_array *array;
- u32 elem_size, array_size;
+ u64 mask64;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
@@ -36,12 +38,33 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
elem_size = round_up(attr->value_size, 8);
+ max_entries = attr->max_entries;
+
+ /* On 32 bit archs roundup_pow_of_two() with max_entries that has
+ * upper most bit set in u32 space is undefined behavior due to
+ * resulting 1U << 32, so do it manually here in u64 space.
+ */
+ mask64 = fls_long(max_entries - 1);
+ mask64 = 1ULL << mask64;
+ mask64 -= 1;
+
+ index_mask = mask64;
+ if (unpriv) {
+ /* round up array size to nearest power of 2,
+ * since cpu will speculate within index_mask limits
+ */
+ max_entries = index_mask + 1;
+ /* Check for overflows. */
+ if (max_entries < attr->max_entries)
+ return ERR_PTR(-E2BIG);
+ }
+
/* check round_up into zero and u32 overflow */
if (elem_size == 0 ||
- attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size)
+ max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size)
return ERR_PTR(-ENOMEM);
- array_size = sizeof(*array) + attr->max_entries * elem_size;
+ array_size = sizeof(*array) + max_entries * elem_size;
/* allocate all map elements and zero-initialize them */
array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
@@ -50,6 +73,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
if (!array)
return ERR_PTR(-ENOMEM);
}
+ array->index_mask = index_mask;
+ array->map.unpriv_array = unpriv;
/* copy mandatory map attributes */
array->map.key_size = attr->key_size;
@@ -70,14 +95,14 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
if (index >= array->map.max_entries)
return NULL;
- return array->value + array->elem_size * index;
+ return array->value + array->elem_size * (index & array->index_mask);
}
/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
- u32 index = *(u32 *)key;
+ u32 index = key ? *(u32 *)key : U32_MAX;
u32 *next = (u32 *)next_key;
if (index >= array->map.max_entries) {
@@ -111,7 +136,9 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
/* all elements already exist */
return -EEXIST;
- memcpy(array->value + array->elem_size * index, value, map->value_size);
+ memcpy(array->value +
+ array->elem_size * (index & array->index_mask),
+ value, map->value_size);
return 0;
}
@@ -243,9 +270,7 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
static void prog_fd_array_put_ptr(void *ptr)
{
- struct bpf_prog *prog = ptr;
-
- bpf_prog_put_rcu(prog);
+ bpf_prog_put(ptr);
}
/* decrement refcnt of all bpf_progs that are stored in this map */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 334b1bdd572c..eb52d11fdaa7 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -137,6 +137,77 @@ void __bpf_prog_free(struct bpf_prog *fp)
}
EXPORT_SYMBOL_GPL(__bpf_prog_free);
+static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn)
+{
+ return BPF_CLASS(insn->code) == BPF_JMP &&
+ /* Call and Exit are both special jumps with no
+ * target inside the BPF instruction image.
+ */
+ BPF_OP(insn->code) != BPF_CALL &&
+ BPF_OP(insn->code) != BPF_EXIT;
+}
+
+static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
+{
+ struct bpf_insn *insn = prog->insnsi;
+ u32 i, insn_cnt = prog->len;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ if (!bpf_is_jmp_and_has_target(insn))
+ continue;
+
+ /* Adjust offset of jmps if we cross boundaries. */
+ if (i < pos && i + insn->off + 1 > pos)
+ insn->off += delta;
+ else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
+ insn->off -= delta;
+ }
+}
+
+struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
+ const struct bpf_insn *patch, u32 len)
+{
+ u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
+ struct bpf_prog *prog_adj;
+
+ /* Since our patchlet doesn't expand the image, we're done. */
+ if (insn_delta == 0) {
+ memcpy(prog->insnsi + off, patch, sizeof(*patch));
+ return prog;
+ }
+
+ insn_adj_cnt = prog->len + insn_delta;
+
+ /* Several new instructions need to be inserted. Make room
+ * for them. Likely, there's no need for a new allocation as
+ * last page could have large enough tailroom.
+ */
+ prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
+ GFP_USER);
+ if (!prog_adj)
+ return NULL;
+
+ prog_adj->len = insn_adj_cnt;
+
+ /* Patching happens in 3 steps:
+ *
+ * 1) Move over tail of insnsi from next instruction onwards,
+ * so we can patch the single target insn with one or more
+ * new ones (patching is always from 1 to n insns, n > 0).
+ * 2) Inject new instructions at the target location.
+ * 3) Adjust branch offsets if necessary.
+ */
+ insn_rest = insn_adj_cnt - off - len;
+
+ memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1,
+ sizeof(*patch) * insn_rest);
+ memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len);
+
+ bpf_adj_branches(prog_adj, off, insn_delta);
+
+ return prog_adj;
+}
+
#ifdef CONFIG_BPF_JIT
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
@@ -185,6 +256,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
}
EXPORT_SYMBOL_GPL(__bpf_call_base);
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
/**
* __bpf_prog_run - run eBPF program on a given context
* @ctx: is the data we are operating on
@@ -372,7 +444,7 @@ select_insn:
DST = tmp;
CONT;
ALU_MOD_X:
- if (unlikely(SRC == 0))
+ if (unlikely((u32)SRC == 0))
return 0;
tmp = (u32) DST;
DST = do_div(tmp, (u32) SRC);
@@ -391,7 +463,7 @@ select_insn:
DST = div64_u64(DST, SRC);
CONT;
ALU_DIV_X:
- if (unlikely(SRC == 0))
+ if (unlikely((u32)SRC == 0))
return 0;
tmp = (u32) DST;
do_div(tmp, (u32) SRC);
@@ -446,7 +518,7 @@ select_insn:
struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog;
- u64 index = BPF_R3;
+ u32 index = BPF_R3;
if (unlikely(index >= array->map.max_entries))
goto out;
@@ -654,6 +726,13 @@ load_byte:
return 0;
}
+#else
+static unsigned int __bpf_prog_ret0(void *ctx, const struct bpf_insn *insn)
+{
+ return 0;
+}
+#endif
+
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
@@ -700,9 +779,23 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
*/
int bpf_prog_select_runtime(struct bpf_prog *fp)
{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
fp->bpf_func = (void *) __bpf_prog_run;
-
+#else
+ fp->bpf_func = (void *) __bpf_prog_ret0;
+#endif
+
+ /* eBPF JITs can rewrite the program in case constant
+ * blinding is active. However, in case of error during
+ * blinding, bpf_int_jit_compile() must always return a
+ * valid program, which in this case would simply not
+ * be JITed, but falls back to the interpreter.
+ */
bpf_int_jit_compile(fp);
+#ifdef CONFIG_BPF_JIT_ALWAYS_ON
+ if (!fp->jited)
+ return -ENOTSUPP;
+#endif
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 34777b3746fa..a35abe048239 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -169,12 +169,15 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
struct hlist_head *head;
struct htab_elem *l, *next_l;
u32 hash, key_size;
- int i;
+ int i = 0;
WARN_ON_ONCE(!rcu_read_lock_held());
key_size = map->key_size;
+ if (!key)
+ goto find_first_elem;
+
hash = htab_map_hash(key, key_size);
head = select_bucket(htab, hash);
@@ -182,10 +185,8 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
/* lookup the key */
l = lookup_elem_raw(head, hash, key, key_size);
- if (!l) {
- i = 0;
+ if (!l)
goto find_first_elem;
- }
/* key was found, get next key in the same bucket */
next_l = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&l->hash_node)),
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4e32cc94edd9..04fc1022ad9f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -390,14 +390,18 @@ static int map_get_next_key(union bpf_attr *attr)
if (IS_ERR(map))
return PTR_ERR(map);
- err = -ENOMEM;
- key = kmalloc(map->key_size, GFP_USER);
- if (!key)
- goto err_put;
-
- err = -EFAULT;
- if (copy_from_user(key, ukey, map->key_size) != 0)
- goto free_key;
+ if (ukey) {
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_USER);
+ if (!key)
+ goto err_put;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+ } else {
+ key = NULL;
+ }
err = -ENOMEM;
next_key = kmalloc(map->key_size, GFP_USER);
@@ -447,57 +451,6 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl)
list_add(&tl->list_node, &bpf_prog_types);
}
-/* fixup insn->imm field of bpf_call instructions:
- * if (insn->imm == BPF_FUNC_map_lookup_elem)
- * insn->imm = bpf_map_lookup_elem - __bpf_call_base;
- * else if (insn->imm == BPF_FUNC_map_update_elem)
- * insn->imm = bpf_map_update_elem - __bpf_call_base;
- * else ...
- *
- * this function is called after eBPF program passed verification
- */
-static void fixup_bpf_calls(struct bpf_prog *prog)
-{
- const struct bpf_func_proto *fn;
- int i;
-
- for (i = 0; i < prog->len; i++) {
- struct bpf_insn *insn = &prog->insnsi[i];
-
- if (insn->code == (BPF_JMP | BPF_CALL)) {
- /* we reach here when program has bpf_call instructions
- * and it passed bpf_check(), means that
- * ops->get_func_proto must have been supplied, check it
- */
- BUG_ON(!prog->aux->ops->get_func_proto);
-
- if (insn->imm == BPF_FUNC_get_route_realm)
- prog->dst_needed = 1;
- if (insn->imm == BPF_FUNC_get_prandom_u32)
- bpf_user_rnd_init_once();
- if (insn->imm == BPF_FUNC_tail_call) {
- /* mark bpf_tail_call as different opcode
- * to avoid conditional branch in
- * interpeter for every normal call
- * and to prevent accidental JITing by
- * JIT compiler that doesn't support
- * bpf_tail_call yet
- */
- insn->imm = 0;
- insn->code |= BPF_X;
- continue;
- }
-
- fn = prog->aux->ops->get_func_proto(insn->imm);
- /* all functions that have prototype and verifier allowed
- * programs to call them, must be real in-kernel functions
- */
- BUG_ON(!fn->func);
- insn->imm = fn->func - __bpf_call_base;
- }
- }
-}
-
/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
@@ -534,7 +487,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
free_uid(user);
}
-static void __prog_put_common(struct rcu_head *rcu)
+static void __bpf_prog_put_rcu(struct rcu_head *rcu)
{
struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
@@ -543,17 +496,10 @@ static void __prog_put_common(struct rcu_head *rcu)
bpf_prog_free(aux->prog);
}
-/* version of bpf_prog_put() that is called after a grace period */
-void bpf_prog_put_rcu(struct bpf_prog *prog)
-{
- if (atomic_dec_and_test(&prog->aux->refcnt))
- call_rcu(&prog->aux->rcu, __prog_put_common);
-}
-
void bpf_prog_put(struct bpf_prog *prog)
{
if (atomic_dec_and_test(&prog->aux->refcnt))
- __prog_put_common(&prog->aux->rcu);
+ call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
EXPORT_SYMBOL_GPL(bpf_prog_put);
@@ -561,7 +507,7 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
{
struct bpf_prog *prog = filp->private_data;
- bpf_prog_put_rcu(prog);
+ bpf_prog_put(prog);
return 0;
}
@@ -680,9 +626,6 @@ static int bpf_prog_load(union bpf_attr *attr)
if (err < 0)
goto free_used_maps;
- /* fixup BPF_CALL->imm field */
- fixup_bpf_calls(prog);
-
/* eBPF program is ready to be JITed */
err = bpf_prog_select_runtime(prog);
if (err < 0)
@@ -727,7 +670,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
union bpf_attr attr = {};
int err;
- if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled)
+ if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
return -EPERM;
if (!access_ok(VERIFY_READ, uattr, 1))
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2cbfba78d3db..c43ca9857479 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -186,6 +186,15 @@ struct verifier_stack_elem {
struct verifier_stack_elem *next;
};
+struct bpf_insn_aux_data {
+ union {
+ enum bpf_reg_type ptr_type; /* pointer type for load/store insns */
+ struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */
+ };
+ int sanitize_stack_off; /* stack slot to be cleared */
+ bool seen; /* this insn was processed by the verifier */
+};
+
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
/* single container for all structs
@@ -200,6 +209,7 @@ struct verifier_env {
struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
u32 used_map_cnt; /* number of used maps */
bool allow_ptr_leaks;
+ struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
};
/* verbose verifier prints what it's seeing
@@ -313,7 +323,8 @@ static const char *const bpf_jmp_string[16] = {
[BPF_EXIT >> 4] = "exit",
};
-static void print_bpf_insn(struct bpf_insn *insn)
+static void print_bpf_insn(const struct verifier_env *env,
+ const struct bpf_insn *insn)
{
u8 class = BPF_CLASS(insn->code);
@@ -377,9 +388,19 @@ static void print_bpf_insn(struct bpf_insn *insn)
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->src_reg, insn->imm);
- } else if (BPF_MODE(insn->code) == BPF_IMM) {
- verbose("(%02x) r%d = 0x%x\n",
- insn->code, insn->dst_reg, insn->imm);
+ } else if (BPF_MODE(insn->code) == BPF_IMM &&
+ BPF_SIZE(insn->code) == BPF_DW) {
+ /* At this point, we already made sure that the second
+ * part of the ldimm64 insn is accessible.
+ */
+ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+ bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+
+ if (map_ptr && !env->allow_ptr_leaks)
+ imm = 0;
+
+ verbose("(%02x) r%d = 0x%llx\n", insn->code,
+ insn->dst_reg, (unsigned long long)imm);
} else {
verbose("BUG_ld_%02x\n", insn->code);
return;
@@ -549,10 +570,11 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
/* check_stack_read/write functions track spill/fill of registers,
* stack boundary and alignment are checked in check_mem_access()
*/
-static int check_stack_write(struct verifier_state *state, int off, int size,
- int value_regno)
+static int check_stack_write(struct verifier_env *env,
+ struct verifier_state *state, int off,
+ int size, int value_regno, int insn_idx)
{
- int i;
+ int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
* so it's aligned access and [off, off + size) are within stack limits
*/
@@ -567,15 +589,37 @@ static int check_stack_write(struct verifier_state *state, int off, int size,
}
/* save register state */
- state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
- state->regs[value_regno];
-
- for (i = 0; i < BPF_REG_SIZE; i++)
+ state->spilled_regs[spi] = state->regs[value_regno];
+
+ for (i = 0; i < BPF_REG_SIZE; i++) {
+ if (state->stack_slot_type[MAX_BPF_STACK + off + i] == STACK_MISC &&
+ !env->allow_ptr_leaks) {
+ int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
+ int soff = (-spi - 1) * BPF_REG_SIZE;
+
+ /* detected reuse of integer stack slot with a pointer
+ * which means either llvm is reusing stack slot or
+ * an attacker is trying to exploit CVE-2018-3639
+ * (speculative store bypass)
+ * Have to sanitize that slot with preemptive
+ * store of zero.
+ */
+ if (*poff && *poff != soff) {
+ /* disallow programs where single insn stores
+ * into two different stack slots, since verifier
+ * cannot sanitize them
+ */
+ verbose("insn %d cannot access two stack slots fp%d and fp%d",
+ insn_idx, *poff, soff);
+ return -EINVAL;
+ }
+ *poff = soff;
+ }
state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL;
+ }
} else {
/* regular write of data into stack */
- state->spilled_regs[(MAX_BPF_STACK + off) / BPF_REG_SIZE] =
- (struct reg_state) {};
+ state->spilled_regs[spi] = (struct reg_state) {};
for (i = 0; i < size; i++)
state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC;
@@ -663,13 +707,20 @@ static bool is_pointer_value(struct verifier_env *env, int regno)
}
}
+static bool is_ctx_reg(struct verifier_env *env, int regno)
+{
+ const struct reg_state *reg = &env->cur_state.regs[regno];
+
+ return reg->type == PTR_TO_CTX;
+}
+
/* check whether memory at (regno + off) is accessible for t = (read | write)
* if t==write, value_regno is a register which value is stored into memory
* if t==read, value_regno is a register which will receive the value from memory
* if t==write && value_regno==-1, some unknown value is stored into memory
* if t==read && value_regno==-1, don't care what we read from memory
*/
-static int check_mem_access(struct verifier_env *env, u32 regno, int off,
+static int check_mem_access(struct verifier_env *env, int insn_idx, u32 regno, int off,
int bpf_size, enum bpf_access_type t,
int value_regno)
{
@@ -721,7 +772,8 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
verbose("attempt to corrupt spilled pointer on stack\n");
return -EACCES;
}
- err = check_stack_write(state, off, size, value_regno);
+ err = check_stack_write(env, state, off, size,
+ value_regno, insn_idx);
} else {
err = check_stack_read(state, off, size, value_regno);
}
@@ -733,7 +785,7 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off,
return err;
}
-static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
+static int check_xadd(struct verifier_env *env, int insn_idx, struct bpf_insn *insn)
{
struct reg_state *regs = env->cur_state.regs;
int err;
@@ -754,14 +806,25 @@ static int check_xadd(struct verifier_env *env, struct bpf_insn *insn)
if (err)
return err;
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose("R%d leaks addr into mem\n", insn->src_reg);
+ return -EACCES;
+ }
+
+ if (is_ctx_reg(env, insn->dst_reg)) {
+ verbose("BPF_XADD stores into R%d context is not allowed\n",
+ insn->dst_reg);
+ return -EACCES;
+ }
+
/* check whether atomic_add can read the memory */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, -1);
if (err)
return err;
/* check whether atomic_add can write into the same memory */
- return check_mem_access(env, insn->dst_reg, insn->off,
+ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1);
}
@@ -929,7 +992,7 @@ error:
return -EINVAL;
}
-static int check_call(struct verifier_env *env, int func_id)
+static int check_call(struct verifier_env *env, int func_id, int insn_idx)
{
struct verifier_state *state = &env->cur_state;
const struct bpf_func_proto *fn = NULL;
@@ -965,6 +1028,13 @@ static int check_call(struct verifier_env *env, int func_id)
err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &map);
if (err)
return err;
+ if (func_id == BPF_FUNC_tail_call) {
+ if (map == NULL) {
+ verbose("verifier bug\n");
+ return -EINVAL;
+ }
+ env->insn_aux_data[insn_idx].map_ptr = map;
+ }
err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &map);
if (err)
return err;
@@ -1028,7 +1098,8 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
}
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
- (insn->imm != 16 && insn->imm != 32 && insn->imm != 64)) {
+ (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
+ BPF_CLASS(insn->code) == BPF_ALU64) {
verbose("BPF_END uses reserved fields\n");
return -EINVAL;
}
@@ -1089,7 +1160,8 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
regs[insn->dst_reg].type = UNKNOWN_VALUE;
regs[insn->dst_reg].map_ptr = NULL;
}
- } else {
+ } else if (BPF_CLASS(insn->code) == BPF_ALU64 ||
+ insn->imm >= 0) {
/* case: R = imm
* remember the value we stored into this reg
*/
@@ -1132,6 +1204,11 @@ static int check_alu_op(struct verifier_env *env, struct bpf_insn *insn)
return -EINVAL;
}
+ if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) {
+ verbose("BPF_ARSH not supported for 32 bit ALU\n");
+ return -EINVAL;
+ }
+
if ((opcode == BPF_LSH || opcode == BPF_RSH ||
opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
@@ -1758,16 +1835,17 @@ static int do_check(struct verifier_env *env)
if (log_level) {
verbose("%d: ", insn_idx);
- print_bpf_insn(insn);
+ print_bpf_insn(env, insn);
}
+ env->insn_aux_data[insn_idx].seen = true;
if (class == BPF_ALU || class == BPF_ALU64) {
err = check_alu_op(env, insn);
if (err)
return err;
} else if (class == BPF_LDX) {
- enum bpf_reg_type src_reg_type;
+ enum bpf_reg_type *prev_src_type, src_reg_type;
/* check for reserved fields is already done */
@@ -1785,27 +1863,30 @@ static int do_check(struct verifier_env *env)
/* check that memory (src_reg + off) is readable,
* the state of dst_reg will be updated by this func
*/
- err = check_mem_access(env, insn->src_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->src_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ,
insn->dst_reg);
if (err)
return err;
- if (BPF_SIZE(insn->code) != BPF_W) {
+ if (BPF_SIZE(insn->code) != BPF_W &&
+ BPF_SIZE(insn->code) != BPF_DW) {
insn_idx++;
continue;
}
- if (insn->imm == 0) {
+ prev_src_type = &env->insn_aux_data[insn_idx].ptr_type;
+
+ if (*prev_src_type == NOT_INIT) {
/* saw a valid insn
* dst_reg = *(u32 *)(src_reg + off)
- * use reserved 'imm' field to mark this insn
+ * save type to validate intersecting paths
*/
- insn->imm = src_reg_type;
+ *prev_src_type = src_reg_type;
- } else if (src_reg_type != insn->imm &&
+ } else if (src_reg_type != *prev_src_type &&
(src_reg_type == PTR_TO_CTX ||
- insn->imm == PTR_TO_CTX)) {
+ *prev_src_type == PTR_TO_CTX)) {
/* ABuser program is trying to use the same insn
* dst_reg = *(u32*) (src_reg + off)
* with different pointer types:
@@ -1818,10 +1899,10 @@ static int do_check(struct verifier_env *env)
}
} else if (class == BPF_STX) {
- enum bpf_reg_type dst_reg_type;
+ enum bpf_reg_type *prev_dst_type, dst_reg_type;
if (BPF_MODE(insn->code) == BPF_XADD) {
- err = check_xadd(env, insn);
+ err = check_xadd(env, insn_idx, insn);
if (err)
return err;
insn_idx++;
@@ -1840,17 +1921,19 @@ static int do_check(struct verifier_env *env)
dst_reg_type = regs[insn->dst_reg].type;
/* check that memory (dst_reg + off) is writeable */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
insn->src_reg);
if (err)
return err;
- if (insn->imm == 0) {
- insn->imm = dst_reg_type;
- } else if (dst_reg_type != insn->imm &&
+ prev_dst_type = &env->insn_aux_data[insn_idx].ptr_type;
+
+ if (*prev_dst_type == NOT_INIT) {
+ *prev_dst_type = dst_reg_type;
+ } else if (dst_reg_type != *prev_dst_type &&
(dst_reg_type == PTR_TO_CTX ||
- insn->imm == PTR_TO_CTX)) {
+ *prev_dst_type == PTR_TO_CTX)) {
verbose("same insn cannot be used with different pointers\n");
return -EINVAL;
}
@@ -1866,8 +1949,14 @@ static int do_check(struct verifier_env *env)
if (err)
return err;
+ if (is_ctx_reg(env, insn->dst_reg)) {
+ verbose("BPF_ST stores into R%d context is not allowed\n",
+ insn->dst_reg);
+ return -EACCES;
+ }
+
/* check that memory (dst_reg + off) is writeable */
- err = check_mem_access(env, insn->dst_reg, insn->off,
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE,
-1);
if (err)
@@ -1885,7 +1974,7 @@ static int do_check(struct verifier_env *env)
return -EINVAL;
}
- err = check_call(env, insn->imm);
+ err = check_call(env, insn->imm, insn_idx);
if (err)
return err;
@@ -1952,6 +2041,7 @@ process_bpf_exit:
return err;
insn_idx++;
+ env->insn_aux_data[insn_idx].seen = true;
} else {
verbose("invalid BPF_LD mode\n");
return -EINVAL;
@@ -2037,7 +2127,7 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env)
/* hold the map. If the program is rejected by verifier,
* the map will be released by release_maps() or it
* will be used by the valid program until it's unloaded
- * and all maps are released in free_bpf_prog_info()
+ * and all maps are released in free_used_maps()
*/
map = bpf_map_inc(map, false);
if (IS_ERR(map)) {
@@ -2081,23 +2171,60 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env)
insn->src_reg = 0;
}
-static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
+/* single env->prog->insni[off] instruction was replaced with the range
+ * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying
+ * [0, off) and [off, end) to new locations, so the patched range stays zero
+ */
+static int adjust_insn_aux_data(struct verifier_env *env, u32 prog_len,
+ u32 off, u32 cnt)
{
- struct bpf_insn *insn = prog->insnsi;
- int insn_cnt = prog->len;
+ struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
int i;
- for (i = 0; i < insn_cnt; i++, insn++) {
- if (BPF_CLASS(insn->code) != BPF_JMP ||
- BPF_OP(insn->code) == BPF_CALL ||
- BPF_OP(insn->code) == BPF_EXIT)
- continue;
+ if (cnt == 1)
+ return 0;
+ new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len);
+ if (!new_data)
+ return -ENOMEM;
+ memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
+ memcpy(new_data + off + cnt - 1, old_data + off,
+ sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
+ for (i = off; i < off + cnt - 1; i++)
+ new_data[i].seen = true;
+ env->insn_aux_data = new_data;
+ vfree(old_data);
+ return 0;
+}
+
+static struct bpf_prog *bpf_patch_insn_data(struct verifier_env *env, u32 off,
+ const struct bpf_insn *patch, u32 len)
+{
+ struct bpf_prog *new_prog;
+
+ new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
+ if (!new_prog)
+ return NULL;
+ if (adjust_insn_aux_data(env, new_prog->len, off, len))
+ return NULL;
+ return new_prog;
+}
+
+/* The verifier does more data flow analysis than llvm and will not explore
+ * branches that are dead at run time. Malicious programs can have dead code
+ * too. Therefore replace all dead at-run-time code with nops.
+ */
+static void sanitize_dead_code(struct verifier_env *env)
+{
+ struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+ struct bpf_insn nop = BPF_MOV64_REG(BPF_REG_0, BPF_REG_0);
+ struct bpf_insn *insn = env->prog->insnsi;
+ const int insn_cnt = env->prog->len;
+ int i;
- /* adjust offset of jmps if necessary */
- if (i < pos && i + insn->off + 1 > pos)
- insn->off += delta;
- else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
- insn->off -= delta;
+ for (i = 0; i < insn_cnt; i++) {
+ if (aux_data[i].seen)
+ continue;
+ memcpy(insn + i, &nop, sizeof(nop));
}
}
@@ -2107,30 +2234,58 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta)
static int convert_ctx_accesses(struct verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
- int insn_cnt = env->prog->len;
+ const int insn_cnt = env->prog->len;
struct bpf_insn insn_buf[16];
struct bpf_prog *new_prog;
- u32 cnt;
- int i;
enum bpf_access_type type;
+ int i, delta = 0;
if (!env->prog->aux->ops->convert_ctx_access)
return 0;
for (i = 0; i < insn_cnt; i++, insn++) {
- if (insn->code == (BPF_LDX | BPF_MEM | BPF_W))
+ u32 cnt;
+
+ if (insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
type = BPF_READ;
- else if (insn->code == (BPF_STX | BPF_MEM | BPF_W))
+ else if (insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_DW))
type = BPF_WRITE;
else
continue;
- if (insn->imm != PTR_TO_CTX) {
- /* clear internal mark */
- insn->imm = 0;
+ if (type == BPF_WRITE &&
+ env->insn_aux_data[i + delta].sanitize_stack_off) {
+ struct bpf_insn patch[] = {
+ /* Sanitize suspicious stack slot with zero.
+ * There are no memory dependencies for this store,
+ * since it's only using frame pointer and immediate
+ * constant of zero
+ */
+ BPF_ST_MEM(BPF_DW, BPF_REG_FP,
+ env->insn_aux_data[i + delta].sanitize_stack_off,
+ 0),
+ /* the original STX instruction will immediately
+ * overwrite the same stack slot with appropriate value
+ */
+ *insn,
+ };
+
+ cnt = ARRAY_SIZE(patch);
+ new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
continue;
}
+ if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
+ continue;
+
cnt = env->prog->aux->ops->
convert_ctx_access(type, insn->dst_reg, insn->src_reg,
insn->off, insn_buf, env->prog);
@@ -2139,34 +2294,107 @@ static int convert_ctx_accesses(struct verifier_env *env)
return -EINVAL;
}
- if (cnt == 1) {
- memcpy(insn, insn_buf, sizeof(*insn));
- continue;
- }
-
- /* several new insns need to be inserted. Make room for them */
- insn_cnt += cnt - 1;
- new_prog = bpf_prog_realloc(env->prog,
- bpf_prog_size(insn_cnt),
- GFP_USER);
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
return -ENOMEM;
- new_prog->len = insn_cnt;
+ delta += cnt - 1;
- memmove(new_prog->insnsi + i + cnt, new_prog->insns + i + 1,
- sizeof(*insn) * (insn_cnt - i - cnt));
+ /* keep walking new program and skip insns we just inserted */
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ }
- /* copy substitute insns in place of load instruction */
- memcpy(new_prog->insnsi + i, insn_buf, sizeof(*insn) * cnt);
+ return 0;
+}
- /* adjust branches in the whole program */
- adjust_branches(new_prog, i, cnt - 1);
+/* fixup insn->imm field of bpf_call instructions
+ *
+ * this function is called after eBPF program passed verification
+ */
+static int fixup_bpf_calls(struct verifier_env *env)
+{
+ struct bpf_prog *prog = env->prog;
+ struct bpf_insn *insn = prog->insnsi;
+ const struct bpf_func_proto *fn;
+ const int insn_cnt = prog->len;
+ struct bpf_insn insn_buf[16];
+ struct bpf_prog *new_prog;
+ struct bpf_map *map_ptr;
+ int i, cnt, delta = 0;
- /* keep walking new program and skip insns we just inserted */
- env->prog = new_prog;
- insn = new_prog->insnsi + i + cnt - 1;
- i += cnt - 1;
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ if (insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
+ insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
+ /* due to JIT bugs clear upper 32-bits of src register
+ * before div/mod operation
+ */
+ insn_buf[0] = BPF_MOV32_REG(insn->src_reg, insn->src_reg);
+ insn_buf[1] = *insn;
+ cnt = 2;
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ if (insn->code != (BPF_JMP | BPF_CALL))
+ continue;
+
+ if (insn->imm == BPF_FUNC_get_route_realm)
+ prog->dst_needed = 1;
+ if (insn->imm == BPF_FUNC_get_prandom_u32)
+ bpf_user_rnd_init_once();
+ if (insn->imm == BPF_FUNC_tail_call) {
+ /* mark bpf_tail_call as different opcode to avoid
+ * conditional branch in the interpeter for every normal
+ * call and to prevent accidental JITing by JIT compiler
+ * that doesn't support bpf_tail_call yet
+ */
+ insn->imm = 0;
+ insn->code |= BPF_X;
+
+ /* instead of changing every JIT dealing with tail_call
+ * emit two extra insns:
+ * if (index >= max_entries) goto out;
+ * index &= array->index_mask;
+ * to avoid out-of-bounds cpu speculation
+ */
+ map_ptr = env->insn_aux_data[i + delta].map_ptr;
+ if (!map_ptr->unpriv_array)
+ continue;
+ insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
+ map_ptr->max_entries, 2);
+ insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
+ container_of(map_ptr,
+ struct bpf_array,
+ map)->index_mask);
+ insn_buf[2] = *insn;
+ cnt = 3;
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
+ fn = prog->aux->ops->get_func_proto(insn->imm);
+ /* all functions that have prototype and verifier allowed
+ * programs to call them, must be real in-kernel functions
+ */
+ if (!fn->func) {
+ verbose("kernel subsystem misconfigured func %d\n",
+ insn->imm);
+ return -EFAULT;
+ }
+ insn->imm = fn->func - __bpf_call_base;
}
return 0;
@@ -2210,6 +2438,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
if (!env)
return -ENOMEM;
+ env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) *
+ (*prog)->len);
+ ret = -ENOMEM;
+ if (!env->insn_aux_data)
+ goto err_free_env;
env->prog = *prog;
/* grab the mutex to protect few globals used by verifier */
@@ -2228,12 +2461,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
/* log_* values have to be sane */
if (log_size < 128 || log_size > UINT_MAX >> 8 ||
log_level == 0 || log_ubuf == NULL)
- goto free_env;
+ goto err_unlock;
ret = -ENOMEM;
log_buf = vmalloc(log_size);
if (!log_buf)
- goto free_env;
+ goto err_unlock;
} else {
log_level = 0;
}
@@ -2262,9 +2495,15 @@ skip_full_check:
free_states(env);
if (ret == 0)
+ sanitize_dead_code(env);
+
+ if (ret == 0)
/* program is valid, convert *(u32*)(ctx + off) accesses */
ret = convert_ctx_accesses(env);
+ if (ret == 0)
+ ret = fixup_bpf_calls(env);
+
if (log_level && log_len >= log_size - 1) {
BUG_ON(log_len >= log_size);
/* verifier log exceeded user supplied buffer */
@@ -2302,14 +2541,16 @@ skip_full_check:
free_log_buf:
if (log_level)
vfree(log_buf);
-free_env:
if (!env->prog->aux->used_maps)
/* if we didn't copy map pointers into bpf_prog_info, release
- * them now. Otherwise free_bpf_prog_info() will release them.
+ * them now. Otherwise free_used_maps() will release them.
*/
release_maps(env);
*prog = env->prog;
- kfree(env);
+err_unlock:
mutex_unlock(&bpf_verifier_lock);
+ vfree(env->insn_aux_data);
+err_free_env:
+ kfree(env);
return ret;
}
diff --git a/kernel/capability.c b/kernel/capability.c
index 00411c82dac5..4984e1f552eb 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -457,6 +457,19 @@ bool file_ns_capable(const struct file *file, struct user_namespace *ns,
EXPORT_SYMBOL(file_ns_capable);
/**
+ * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode?
+ * @ns: The user namespace in question
+ * @inode: The inode in question
+ *
+ * Return true if the inode uid and gid are within the namespace.
+ */
+bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode)
+{
+ return kuid_has_mapping(ns, inode->i_uid) &&
+ kgid_has_mapping(ns, inode->i_gid);
+}
+
+/**
* capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
* @inode: The inode in question
* @cap: The capability in question
@@ -469,7 +482,26 @@ bool capable_wrt_inode_uidgid(const struct inode *inode, int cap)
{
struct user_namespace *ns = current_user_ns();
- return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) &&
- kgid_has_mapping(ns, inode->i_gid);
+ return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, inode);
}
EXPORT_SYMBOL(capable_wrt_inode_uidgid);
+
+/**
+ * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace
+ * @tsk: The task that may be ptraced
+ * @ns: The user namespace to search for CAP_SYS_PTRACE in
+ *
+ * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE
+ * in the specified user namespace.
+ */
+bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns)
+{
+ int ret = 0; /* An absent tracer adds no restrictions */
+ const struct cred *cred;
+ rcu_read_lock();
+ cred = rcu_dereference(tsk->ptracer_cred);
+ if (cred)
+ ret = security_capable_noaudit(cred, ns, CAP_SYS_PTRACE);
+ rcu_read_unlock();
+ return (ret == 0);
+}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a3424f28aaf4..96f0fe9441af 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -236,6 +236,9 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css,
*/
static bool cgroup_ssid_enabled(int ssid)
{
+ if (CGROUP_SUBSYS_COUNT == 0)
+ return false;
+
return static_key_enabled(cgroup_subsys_enabled_key[ssid]);
}
@@ -781,6 +784,8 @@ static void put_css_set_locked(struct css_set *cset)
static void put_css_set(struct css_set *cset)
{
+ unsigned long flags;
+
/*
* Ensure that the refcount doesn't hit zero while any readers
* can see it. Similar to atomic_dec_and_lock(), but for an
@@ -789,9 +794,9 @@ static void put_css_set(struct css_set *cset)
if (atomic_add_unless(&cset->refcount, -1, 1))
return;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irqsave(&css_set_lock, flags);
put_css_set_locked(cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irqrestore(&css_set_lock, flags);
}
/*
@@ -1014,11 +1019,11 @@ static struct css_set *find_css_set(struct css_set *old_cset,
/* First see if we already have a cgroup group that matches
* the desired set */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cset = find_existing_css_set(old_cset, cgrp, template);
if (cset)
get_css_set(cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (cset)
return cset;
@@ -1046,7 +1051,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
* find_existing_css_set() */
memcpy(cset->subsys, template, sizeof(cset->subsys));
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
/* Add reference counts and links from the new css_set. */
list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) {
struct cgroup *c = link->cgrp;
@@ -1072,7 +1077,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
css_get(css);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return cset;
}
@@ -1136,7 +1141,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
* Release all the links from cset_links to this hierarchy's
* root cgroup
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) {
list_del(&link->cset_link);
@@ -1144,7 +1149,7 @@ static void cgroup_destroy_root(struct cgroup_root *root)
kfree(link);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
if (!list_empty(&root->root_list)) {
list_del(&root->root_list);
@@ -1548,11 +1553,11 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
ss->root = dst_root;
css->cgroup = dcgrp;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
hash_for_each(css_set_table, i, cset, hlist)
list_move_tail(&cset->e_cset_node[ss->id],
&dcgrp->e_csets[ss->id]);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
src_root->subsys_mask &= ~(1 << ssid);
scgrp->subtree_control &= ~(1 << ssid);
@@ -1829,7 +1834,7 @@ static void cgroup_enable_task_cg_lists(void)
{
struct task_struct *p, *g;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
if (use_task_css_set_links)
goto out_unlock;
@@ -1854,8 +1859,12 @@ static void cgroup_enable_task_cg_lists(void)
* entry won't be deleted though the process has exited.
* Do it while holding siglock so that we don't end up
* racing against cgroup_exit().
+ *
+ * Interrupts were already disabled while acquiring
+ * the css_set_lock, so we do not need to disable it
+ * again when acquiring the sighand->siglock here.
*/
- spin_lock_irq(&p->sighand->siglock);
+ spin_lock(&p->sighand->siglock);
if (!(p->flags & PF_EXITING)) {
struct css_set *cset = task_css_set(p);
@@ -1864,11 +1873,11 @@ static void cgroup_enable_task_cg_lists(void)
list_add_tail(&p->cg_list, &cset->tasks);
get_css_set(cset);
}
- spin_unlock_irq(&p->sighand->siglock);
+ spin_unlock(&p->sighand->siglock);
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
out_unlock:
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
static void init_cgroup_housekeeping(struct cgroup *cgrp)
@@ -1973,13 +1982,13 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
* Link the root cgroup in this hierarchy into all the css_set
* objects.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
hash_for_each(css_set_table, i, cset, hlist) {
link_css_set(&tmp_links, cset, root_cgrp);
if (css_set_populated(cset))
cgroup_update_populated(root_cgrp, true);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
BUG_ON(!list_empty(&root_cgrp->self.children));
BUG_ON(atomic_read(&root->nr_cgrps) != 1);
@@ -2212,7 +2221,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
char *path = NULL;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id);
@@ -2225,7 +2234,7 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
path = buf;
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
return path;
}
@@ -2400,7 +2409,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
* the new cgroup. There are no failure cases after here, so this
* is the commit point.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(cset, &tset->src_csets, mg_node) {
list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) {
struct css_set *from_cset = task_css_set(task);
@@ -2411,7 +2420,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
put_css_set_locked(from_cset);
}
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/*
* Migration is committed, all target tasks are now on dst_csets.
@@ -2440,13 +2449,13 @@ out_cancel_attach:
}
}
out_release_tset:
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_splice_init(&tset->dst_csets, &tset->src_csets);
list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) {
list_splice_tail_init(&cset->mg_tasks, &cset->tasks);
list_del_init(&cset->mg_node);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return ret;
}
@@ -2463,14 +2472,14 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
lockdep_assert_held(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
cset->mg_src_cgrp = NULL;
cset->mg_dst_cset = NULL;
list_del_init(&cset->mg_preload_node);
put_css_set_locked(cset);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/**
@@ -2620,7 +2629,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
* already PF_EXITING could be freed from underneath us unless we
* take an rcu_read_lock.
*/
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
task = leader;
do {
@@ -2629,7 +2638,7 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup,
break;
} while_each_thread(leader, task);
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return cgroup_taskset_migrate(&tset, cgrp);
}
@@ -2650,7 +2659,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
int ret;
/* look up all src csets */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
task = leader;
do {
@@ -2660,7 +2669,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
break;
} while_each_thread(leader, task);
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* prepare dst csets and commit */
ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets);
@@ -2685,7 +2694,8 @@ static int cgroup_procs_write_permission(struct task_struct *task,
*/
if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
!uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->euid, tcred->suid))
+ !uid_eq(cred->euid, tcred->suid) &&
+ !ns_capable(tcred->user_ns, CAP_SYS_NICE))
ret = -EACCES;
if (!ret && cgroup_on_dfl(dst_cgrp)) {
@@ -2693,9 +2703,9 @@ static int cgroup_procs_write_permission(struct task_struct *task,
struct cgroup *cgrp;
struct inode *inode;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
while (!cgroup_is_descendant(dst_cgrp, cgrp))
cgrp = cgroup_parent(cgrp);
@@ -2749,11 +2759,12 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
tsk = tsk->group_leader;
/*
- * Workqueue threads may acquire PF_NO_SETAFFINITY and become
- * trapped in a cpuset, or RT worker may be born in a cgroup
- * with no rt_runtime allocated. Just say no.
+ * kthreads may acquire PF_NO_SETAFFINITY during initialization.
+ * If userland migrates such a kthread to a non-root cgroup, it can
+ * become trapped in a cpuset, or RT kthread may be born in a
+ * cgroup with no rt_runtime allocated. Just say no.
*/
- if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
+ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
ret = -EINVAL;
goto out_unlock_rcu;
}
@@ -2796,9 +2807,9 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
if (root == &cgrp_dfl_root)
continue;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
from_cgrp = task_cgroup_from_root(from, root);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
retval = cgroup_attach_task(from_cgrp, tsk, false);
if (retval)
@@ -2923,7 +2934,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
percpu_down_write(&cgroup_threadgroup_rwsem);
/* look up all csses currently attached to @cgrp's subtree */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
struct cgrp_cset_link *link;
@@ -2935,14 +2946,14 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
cgroup_migrate_add_src(link->cset, cgrp,
&preloaded_csets);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* NULL dst indicates self on default hierarchy */
ret = cgroup_migrate_prepare_dst(NULL, &preloaded_csets);
if (ret)
goto out_finish;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) {
struct task_struct *task, *ntask;
@@ -2954,7 +2965,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list)
cgroup_taskset_add(task, &tset);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
ret = cgroup_taskset_migrate(&tset, cgrp);
out_finish:
@@ -3637,10 +3648,10 @@ static int cgroup_task_count(const struct cgroup *cgrp)
int count = 0;
struct cgrp_cset_link *link;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
count += atomic_read(&link->cset->refcount);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return count;
}
@@ -3978,7 +3989,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
memset(it, 0, sizeof(*it));
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
it->ss = css->ss;
@@ -3991,7 +4002,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
css_task_iter_advance_css_set(it);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/**
@@ -4009,7 +4020,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
it->cur_task = NULL;
}
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
if (it->task_pos) {
it->cur_task = list_entry(it->task_pos, struct task_struct,
@@ -4018,7 +4029,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
css_task_iter_advance(it);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return it->cur_task;
}
@@ -4032,10 +4043,10 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
void css_task_iter_end(struct css_task_iter *it)
{
if (it->cur_cset) {
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_del(&it->iters_node);
put_css_set_locked(it->cur_cset);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
if (it->cur_task)
@@ -4064,10 +4075,10 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
mutex_lock(&cgroup_mutex);
/* all tasks in @from are being moved, all csets are source */
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &from->cset_links, cset_link)
cgroup_migrate_add_src(link->cset, to, &preloaded_csets);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
ret = cgroup_migrate_prepare_dst(to, &preloaded_csets);
if (ret)
@@ -4079,7 +4090,11 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
*/
do {
css_task_iter_start(&from->self, &it);
- task = css_task_iter_next(&it);
+
+ do {
+ task = css_task_iter_next(&it);
+ } while (task && (task->flags & PF_EXITING));
+
if (task)
get_task_struct(task);
css_task_iter_end(&it);
@@ -5172,10 +5187,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
*/
cgrp->self.flags &= ~CSS_ONLINE;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
link->cset->dead = true;
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
/* initiate massacre of all css's */
for_each_css(css, ssid, cgrp)
@@ -5325,6 +5340,12 @@ int __init cgroup_init(void)
BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
+ /*
+ * The latency of the synchronize_sched() is too high for cgroups,
+ * avoid it at the cost of forcing all readers into the slow path.
+ */
+ rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
+
mutex_lock(&cgroup_mutex);
/* Add init_css_set to the hash table */
@@ -5428,7 +5449,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
goto out;
mutex_lock(&cgroup_mutex);
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
for_each_root(root) {
struct cgroup_subsys *ss;
@@ -5480,7 +5501,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
retval = 0;
out_unlock:
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
mutex_unlock(&cgroup_mutex);
kfree(buf);
out:
@@ -5641,13 +5662,13 @@ void cgroup_post_fork(struct task_struct *child,
if (use_task_css_set_links) {
struct css_set *cset;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
cset = task_css_set(current);
if (list_empty(&child->cg_list)) {
get_css_set(cset);
css_set_move_task(child, NULL, cset, false);
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
}
/*
@@ -5691,9 +5712,9 @@ void cgroup_exit(struct task_struct *tsk)
cset = task_css_set(tsk);
if (!list_empty(&tsk->cg_list)) {
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
css_set_move_task(tsk, cset, NULL, false);
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
} else {
get_css_set(cset);
}
@@ -5906,7 +5927,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
if (!name_buf)
return -ENOMEM;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
rcu_read_lock();
cset = rcu_dereference(current->cgroups);
list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
@@ -5917,7 +5938,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
c->root->hierarchy_id, name_buf);
}
rcu_read_unlock();
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
kfree(name_buf);
return 0;
}
@@ -5928,7 +5949,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
struct cgroup_subsys_state *css = seq_css(seq);
struct cgrp_cset_link *link;
- spin_lock_bh(&css_set_lock);
+ spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &css->cgroup->cset_links, cset_link) {
struct css_set *cset = link->cset;
struct task_struct *task;
@@ -5951,7 +5972,7 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
overflow:
seq_puts(seq, " ...\n");
}
- spin_unlock_bh(&css_set_lock);
+ spin_unlock_irq(&css_set_lock);
return 0;
}
diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config
new file mode 100644
index 000000000000..d70829033bb7
--- /dev/null
+++ b/kernel/configs/android-base.config
@@ -0,0 +1,160 @@
+# KEEP ALPHABETICALLY SORTED
+# CONFIG_DEVKMEM is not set
+# CONFIG_DEVMEM is not set
+# CONFIG_FHANDLE is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_NFSD is not set
+# CONFIG_NFS_FS is not set
+# CONFIG_OABI_COMPAT is not set
+# CONFIG_SYSVIPC is not set
+# CONFIG_USELIB is not set
+CONFIG_ANDROID=y
+CONFIG_ANDROID_BINDER_IPC=y
+CONFIG_ANDROID_LOW_MEMORY_KILLER=y
+CONFIG_ARMV8_DEPRECATED=y
+CONFIG_ASHMEM=y
+CONFIG_AUDIT=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_BPF=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEBUG=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CP15_BARRIER_EMULATION=y
+CONFIG_DEFAULT_SECURITY_SELINUX=y
+CONFIG_EMBEDDED=y
+CONFIG_FB=y
+CONFIG_HARDENED_USERCOPY=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_INET=y
+CONFIG_INET_DIAG_DESTROY=y
+CONFIG_INET_ESP=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_IP6_NF_RAW=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IPV6=y
+CONFIG_IPV6_MIP6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6_OPTIMISTIC_DAD=y
+CONFIG_IPV6_ROUTER_PREF=y
+CONFIG_IPV6_ROUTE_INFO=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_ARPFILTER=y
+CONFIG_IP_NF_ARPTABLES=y
+CONFIG_IP_NF_ARP_MANGLE=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_IP_NF_MATCH_AH=y
+CONFIG_IP_NF_MATCH_ECN=y
+CONFIG_IP_NF_MATCH_TTL=y
+CONFIG_IP_NF_NAT=y
+CONFIG_IP_NF_RAW=y
+CONFIG_IP_NF_SECURITY=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_TARGET_NETMAP=y
+CONFIG_IP_NF_TARGET_REDIRECT=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_TPROXY=y
+CONFIG_NETFILTER_XT_MATCH_COMMENT=y
+CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_CONNMARK=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y
+CONFIG_NETFILTER_XT_MATCH_HELPER=y
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=y
+CONFIG_NETFILTER_XT_MATCH_LENGTH=y
+CONFIG_NETFILTER_XT_MATCH_LIMIT=y
+CONFIG_NETFILTER_XT_MATCH_MAC=y
+CONFIG_NETFILTER_XT_MATCH_MARK=y
+CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_QUOTA=y
+CONFIG_NETFILTER_XT_MATCH_SOCKET=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NETFILTER_XT_MATCH_STATISTIC=y
+CONFIG_NETFILTER_XT_MATCH_STRING=y
+CONFIG_NETFILTER_XT_MATCH_TIME=y
+CONFIG_NETFILTER_XT_MATCH_U32=y
+CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y
+CONFIG_NETFILTER_XT_TARGET_CONNMARK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y
+CONFIG_NETFILTER_XT_TARGET_MARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_TARGET_TPROXY=y
+CONFIG_NETFILTER_XT_TARGET_TRACE=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_CLS_U32=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_U32=y
+CONFIG_NET_KEY=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_AMANDA=y
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_H323=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_NETBIOS_NS=y
+CONFIG_NF_CONNTRACK_PPTP=y
+CONFIG_NF_CONNTRACK_SANE=y
+CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_TFTP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
+CONFIG_NF_NAT=y
+CONFIG_NO_HZ=y
+CONFIG_PACKET=y
+CONFIG_PM_AUTOSLEEP=y
+CONFIG_PM_WAKELOCKS=y
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_MPPE=y
+CONFIG_PREEMPT=y
+CONFIG_QUOTA=y
+CONFIG_RANDOMIZE_BASE=y
+CONFIG_RTC_CLASS=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECCOMP=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SETEND_EMULATION=y
+CONFIG_STAGING=y
+CONFIG_SWP_EMULATION=y
+CONFIG_SYNC=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_CONFIGFS=y
+CONFIG_USB_CONFIGFS_F_FS=y
+CONFIG_USB_CONFIGFS_F_MIDI=y
+CONFIG_USB_OTG_WAKELOCK=y
+CONFIG_XFRM_USER=y
diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config
new file mode 100644
index 000000000000..297756be369c
--- /dev/null
+++ b/kernel/configs/android-recommended.config
@@ -0,0 +1,125 @@
+# KEEP ALPHABETICALLY SORTED
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_NF_CONNTRACK_SIP is not set
+# CONFIG_PM_WAKELOCKS_GC is not set
+# CONFIG_VT is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_COMPACTION=y
+CONFIG_DEBUG_RODATA=y
+CONFIG_DM_CRYPT=y
+CONFIG_DM_UEVENT=y
+CONFIG_DM_VERITY=y
+CONFIG_DM_VERITY_FEC=y
+CONFIG_DRAGONRISE_FF=y
+CONFIG_ENABLE_DEFAULT_TRACERS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_FUSE_FS=y
+CONFIG_GREENASIA_FF=y
+CONFIG_HIDRAW=y
+CONFIG_HID_A4TECH=y
+CONFIG_HID_ACRUX=y
+CONFIG_HID_ACRUX_FF=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+CONFIG_HID_ELECOM=y
+CONFIG_HID_EMS_FF=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_GREENASIA=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_HOLTEK=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_KEYTOUCH=y
+CONFIG_HID_KYE=y
+CONFIG_HID_LCPOWER=y
+CONFIG_HID_LOGITECH=y
+CONFIG_HID_LOGITECH_DJ=y
+CONFIG_HID_MAGICMOUSE=y
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_MULTITOUCH=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_PICOLCD=y
+CONFIG_HID_PRIMAX=y
+CONFIG_HID_PRODIKEYS=y
+CONFIG_HID_ROCCAT=y
+CONFIG_HID_SAITEK=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SPEEDLINK=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_TIVO=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_UCLOGIC=y
+CONFIG_HID_WACOM=y
+CONFIG_HID_WALTOP=y
+CONFIG_HID_WIIMOTE=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_HID_ZYDACRON=y
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_GPIO=y
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_INPUT_MISC=y
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_UINPUT=y
+CONFIG_ION=y
+CONFIG_JOYSTICK_XPAD=y
+CONFIG_JOYSTICK_XPAD_FF=y
+CONFIG_JOYSTICK_XPAD_LEDS=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KSM=y
+CONFIG_LOGIG940_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_LOGITECH_FF=y
+CONFIG_MD=y
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_MSDOS_FS=y
+CONFIG_PANIC_TIMEOUT=5
+CONFIG_PANTHERLORD_FF=y
+CONFIG_PERF_EVENTS=y
+CONFIG_PM_DEBUG=y
+CONFIG_PM_RUNTIME=y
+CONFIG_PM_WAKELOCKS_LIMIT=0
+CONFIG_POWER_SUPPLY=y
+CONFIG_PSTORE=y
+CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=y
+CONFIG_SCHEDSTATS=y
+CONFIG_SMARTJOYPLUS_FF=y
+CONFIG_SND=y
+CONFIG_SOUND=y
+CONFIG_SUSPEND_TIME=y
+CONFIG_TABLET_USB_ACECAD=y
+CONFIG_TABLET_USB_AIPTEK=y
+CONFIG_TABLET_USB_GTCO=y
+CONFIG_TABLET_USB_HANWANG=y
+CONFIG_TABLET_USB_KBTAB=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_TASK_XACCT=y
+CONFIG_TIMER_STATS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_UHID=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB_USBNET=y
+CONFIG_VFAT_FS=y
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 85ff5e26e23b..427ec803d455 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -8,6 +8,7 @@
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/sched.h>
+#include <linux/sched/smt.h>
#include <linux/unistd.h>
#include <linux/cpu.h>
#include <linux/oom.h>
@@ -24,6 +25,8 @@
#include <linux/irq.h>
#include <trace/events/power.h>
+#include <trace/events/sched.h>
+
#include "smpboot.h"
#ifdef CONFIG_SMP
@@ -183,15 +186,28 @@ void cpu_hotplug_disable(void)
}
EXPORT_SYMBOL_GPL(cpu_hotplug_disable);
+static void __cpu_hotplug_enable(void)
+{
+ if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n"))
+ return;
+ cpu_hotplug_disabled--;
+}
+
void cpu_hotplug_enable(void)
{
cpu_maps_update_begin();
- WARN_ON(--cpu_hotplug_disabled < 0);
+ __cpu_hotplug_enable();
cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
#endif /* CONFIG_HOTPLUG_CPU */
+/*
+ * Architectures that need SMT-specific errata handling during SMT hotplug
+ * should override this.
+ */
+void __weak arch_smt_update(void) { }
+
/* Need to know about CPUs going up/down? */
int register_cpu_notifier(struct notifier_block *nb)
{
@@ -223,12 +239,6 @@ static int cpu_notify(unsigned long val, void *v)
return __cpu_notify(val, v, -1, NULL);
}
-#ifdef CONFIG_HOTPLUG_CPU
-
-static void cpu_notify_nofail(unsigned long val, void *v)
-{
- BUG_ON(cpu_notify(val, v));
-}
EXPORT_SYMBOL(register_cpu_notifier);
EXPORT_SYMBOL(__register_cpu_notifier);
@@ -246,6 +256,12 @@ void __unregister_cpu_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL(__unregister_cpu_notifier);
+#ifdef CONFIG_HOTPLUG_CPU
+static void cpu_notify_nofail(unsigned long val, void *v)
+{
+ BUG_ON(cpu_notify(val, v));
+}
+
/**
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
* @cpu: a CPU id
@@ -425,8 +441,10 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
out_release:
cpu_hotplug_done();
+ trace_sched_cpu_hotplug(cpu, err, 0);
if (!err)
cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
+ arch_smt_update();
return err;
}
@@ -530,7 +548,8 @@ out_notify:
__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
out:
cpu_hotplug_done();
-
+ trace_sched_cpu_hotplug(cpu, ret, 1);
+ arch_smt_update();
return ret;
}
@@ -623,10 +642,11 @@ void __weak arch_enable_nonboot_cpus_end(void)
void enable_nonboot_cpus(void)
{
int cpu, error;
+ struct device *cpu_device;
/* Allow everyone to use the CPU hotplug again */
cpu_maps_update_begin();
- WARN_ON(--cpu_hotplug_disabled < 0);
+ __cpu_hotplug_enable();
if (cpumask_empty(frozen_cpus))
goto out;
@@ -640,6 +660,12 @@ void enable_nonboot_cpus(void)
trace_suspend_resume(TPS("CPU_ON"), cpu, false);
if (!error) {
pr_info("CPU%d is up\n", cpu);
+ cpu_device = get_cpu_device(cpu);
+ if (!cpu_device)
+ pr_err("%s: failed to get cpu%d device\n",
+ __func__, cpu);
+ else
+ kobject_uevent(&cpu_device->kobj, KOBJ_ONLINE);
continue;
}
pr_warn("Error taking CPU%d up: %d\n", cpu, error);
@@ -827,3 +853,36 @@ void init_cpu_online(const struct cpumask *src)
{
cpumask_copy(to_cpumask(cpu_online_bits), src);
}
+
+enum cpu_mitigations cpu_mitigations = CPU_MITIGATIONS_AUTO;
+
+static int __init mitigations_parse_cmdline(char *arg)
+{
+ if (!strcmp(arg, "off"))
+ cpu_mitigations = CPU_MITIGATIONS_OFF;
+ else if (!strcmp(arg, "auto"))
+ cpu_mitigations = CPU_MITIGATIONS_AUTO;
+
+ return 0;
+}
+early_param("mitigations", mitigations_parse_cmdline);
+
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+ atomic_notifier_chain_register(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+ atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
+
+void idle_notifier_call_chain(unsigned long val)
+{
+ atomic_notifier_call_chain(&idle_notifier, val, NULL);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_call_chain);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b271353d5202..db86d6b609b6 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -60,6 +60,7 @@
#include <linux/cgroup.h>
#include <linux/wait.h>
+struct static_key cpusets_pre_enable_key __read_mostly = STATIC_KEY_INIT_FALSE;
struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;
/* See "Frequency meter" comments, below. */
@@ -98,6 +99,7 @@ struct cpuset {
/* user-configured CPUs and Memory Nodes allow to tasks */
cpumask_var_t cpus_allowed;
+ cpumask_var_t cpus_requested;
nodemask_t mems_allowed;
/* effective CPUs and Memory Nodes allow to tasks */
@@ -173,9 +175,9 @@ typedef enum {
} cpuset_flagbits_t;
/* convenient tests for these bits */
-static inline bool is_cpuset_online(const struct cpuset *cs)
+static inline bool is_cpuset_online(struct cpuset *cs)
{
- return test_bit(CS_ONLINE, &cs->flags);
+ return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css);
}
static inline int is_cpu_exclusive(const struct cpuset *cs)
@@ -397,7 +399,7 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs,
static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
{
- return cpumask_subset(p->cpus_allowed, q->cpus_allowed) &&
+ return cpumask_subset(p->cpus_requested, q->cpus_requested) &&
nodes_subset(p->mems_allowed, q->mems_allowed) &&
is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
is_mem_exclusive(p) <= is_mem_exclusive(q);
@@ -497,7 +499,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
cpuset_for_each_child(c, css, par) {
if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
c != cur &&
- cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
+ cpumask_intersects(trial->cpus_requested, c->cpus_requested))
goto out;
if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
c != cur &&
@@ -956,17 +958,18 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
if (!*buf) {
cpumask_clear(trialcs->cpus_allowed);
} else {
- retval = cpulist_parse(buf, trialcs->cpus_allowed);
+ retval = cpulist_parse(buf, trialcs->cpus_requested);
if (retval < 0)
return retval;
- if (!cpumask_subset(trialcs->cpus_allowed,
- top_cpuset.cpus_allowed))
+ if (!cpumask_subset(trialcs->cpus_requested, cpu_present_mask))
return -EINVAL;
+
+ cpumask_and(trialcs->cpus_allowed, trialcs->cpus_requested, cpu_active_mask);
}
/* Nothing to do if the cpus didn't change */
- if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
+ if (cpumask_equal(cs->cpus_requested, trialcs->cpus_requested))
return 0;
retval = validate_change(cs, trialcs);
@@ -975,6 +978,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
spin_lock_irq(&callback_lock);
cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
+ cpumask_copy(cs->cpus_requested, trialcs->cpus_requested);
spin_unlock_irq(&callback_lock);
/* use trialcs->cpus_allowed as a temp variable */
@@ -1765,7 +1769,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
switch (type) {
case FILE_CPULIST:
- seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed));
+ seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_requested));
break;
case FILE_MEMLIST:
seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed));
@@ -1909,6 +1913,7 @@ static struct cftype files[] = {
{
.name = "memory_pressure",
.read_u64 = cpuset_read_u64,
+ .private = FILE_MEMORY_PRESSURE,
},
{
@@ -1954,11 +1959,14 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
return ERR_PTR(-ENOMEM);
if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL))
goto free_cs;
+ if (!alloc_cpumask_var(&cs->cpus_requested, GFP_KERNEL))
+ goto free_allowed;
if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL))
- goto free_cpus;
+ goto free_requested;
set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
cpumask_clear(cs->cpus_allowed);
+ cpumask_clear(cs->cpus_requested);
nodes_clear(cs->mems_allowed);
cpumask_clear(cs->effective_cpus);
nodes_clear(cs->effective_mems);
@@ -1967,7 +1975,9 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
return &cs->css;
-free_cpus:
+free_requested:
+ free_cpumask_var(cs->cpus_requested);
+free_allowed:
free_cpumask_var(cs->cpus_allowed);
free_cs:
kfree(cs);
@@ -2030,6 +2040,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
cs->mems_allowed = parent->mems_allowed;
cs->effective_mems = parent->mems_allowed;
cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
+ cpumask_copy(cs->cpus_requested, parent->cpus_requested);
cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
spin_unlock_irq(&callback_lock);
out_unlock:
@@ -2064,6 +2075,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
free_cpumask_var(cs->effective_cpus);
free_cpumask_var(cs->cpus_allowed);
+ free_cpumask_var(cs->cpus_requested);
kfree(cs);
}
@@ -2128,8 +2140,11 @@ int __init cpuset_init(void)
BUG();
if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL))
BUG();
+ if (!alloc_cpumask_var(&top_cpuset.cpus_requested, GFP_KERNEL))
+ BUG();
cpumask_setall(top_cpuset.cpus_allowed);
+ cpumask_setall(top_cpuset.cpus_requested);
nodes_setall(top_cpuset.mems_allowed);
cpumask_setall(top_cpuset.effective_cpus);
nodes_setall(top_cpuset.effective_mems);
@@ -2263,7 +2278,7 @@ retry:
goto retry;
}
- cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus);
+ cpumask_and(&new_cpus, cs->cpus_requested, parent_cs(cs)->effective_cpus);
nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems);
cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
@@ -2279,6 +2294,13 @@ retry:
mutex_unlock(&cpuset_mutex);
}
+static bool force_rebuild;
+
+void cpuset_force_rebuild(void)
+{
+ force_rebuild = true;
+}
+
/**
* cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset
*
@@ -2353,8 +2375,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
}
/* rebuild sched domains if cpus_allowed has changed */
- if (cpus_updated)
+ if (cpus_updated || force_rebuild) {
+ force_rebuild = false;
rebuild_sched_domains();
+ }
}
void cpuset_update_active_cpus(bool cpu_online)
@@ -2373,6 +2397,11 @@ void cpuset_update_active_cpus(bool cpu_online)
schedule_work(&cpuset_hotplug_work);
}
+void cpuset_wait_for_hotplug(void)
+{
+ flush_work(&cpuset_hotplug_work);
+}
+
/*
* Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY].
* Call this routine anytime after node_states[N_MEMORY] changes.
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 0874e2edd275..79517e5549f1 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -598,11 +598,11 @@ return_normal:
/*
* Wait for the other CPUs to be notified and be waiting for us:
*/
- time_left = loops_per_jiffy * HZ;
+ time_left = MSEC_PER_SEC;
while (kgdb_do_roundup && --time_left &&
(atomic_read(&masters_in_kgdb) + atomic_read(&slaves_in_kgdb)) !=
online_cpus)
- cpu_relax();
+ udelay(1000);
if (!time_left)
pr_crit("Timed out waiting for secondary CPUs.\n");
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index e1dbf4a2c69e..90ff129c88a2 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -153,13 +153,11 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp)
} else {
kdb_printf("%s: failed to set breakpoint at 0x%lx\n",
__func__, bp->bp_addr);
-#ifdef CONFIG_DEBUG_RODATA
if (!bp->bp_type) {
kdb_printf("Software breakpoints are unavailable.\n"
- " Change the kernel CONFIG_DEBUG_RODATA=n\n"
+ " Boot the kernel with rodata=off\n"
" OR use hw breaks: help bph\n");
}
-#endif
return 1;
}
return 0;
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index fc1ef736253c..d3c5b15c86c1 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -215,8 +215,8 @@ static char *kdb_read(char *buffer, size_t bufsize)
int count;
int i;
int diag, dtab_count;
- int key;
-
+ int key, buf_size, ret;
+ static int last_crlf;
diag = kdbgetintenv("DTABCOUNT", &dtab_count);
if (diag)
@@ -237,6 +237,9 @@ poll_again:
return buffer;
if (key != 9)
tab = 0;
+ if (key != 10 && key != 13)
+ last_crlf = 0;
+
switch (key) {
case 8: /* backspace */
if (cp > buffer) {
@@ -254,7 +257,12 @@ poll_again:
*cp = tmp;
}
break;
- case 13: /* enter */
+ case 10: /* new line */
+ case 13: /* carriage return */
+ /* handle \n after \r */
+ if (last_crlf && last_crlf != key)
+ break;
+ last_crlf = key;
*lastchar++ = '\n';
*lastchar++ = '\0';
if (!KDB_STATE(KGDB_TRANS)) {
@@ -335,9 +343,8 @@ poll_again:
else
p_tmp = tmpbuffer;
len = strlen(p_tmp);
- count = kallsyms_symbol_complete(p_tmp,
- sizeof(tmpbuffer) -
- (p_tmp - tmpbuffer));
+ buf_size = sizeof(tmpbuffer) - (p_tmp - tmpbuffer);
+ count = kallsyms_symbol_complete(p_tmp, buf_size);
if (tab == 2 && count > 0) {
kdb_printf("\n%d symbols are found.", count);
if (count > dtab_count) {
@@ -349,9 +356,13 @@ poll_again:
}
kdb_printf("\n");
for (i = 0; i < count; i++) {
- if (kallsyms_symbol_next(p_tmp, i) < 0)
+ ret = kallsyms_symbol_next(p_tmp, i, buf_size);
+ if (WARN_ON(!ret))
break;
- kdb_printf("%s ", p_tmp);
+ if (ret != -E2BIG)
+ kdb_printf("%s ", p_tmp);
+ else
+ kdb_printf("%s... ", p_tmp);
*(p_tmp + len) = '\0';
}
if (i >= dtab_count)
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 4121345498e0..ebc52c7bd8a6 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1564,6 +1564,7 @@ static int kdb_md(int argc, const char **argv)
int symbolic = 0;
int valid = 0;
int phys = 0;
+ int raw = 0;
kdbgetintenv("MDCOUNT", &mdcount);
kdbgetintenv("RADIX", &radix);
@@ -1573,9 +1574,10 @@ static int kdb_md(int argc, const char **argv)
repeat = mdcount * 16 / bytesperword;
if (strcmp(argv[0], "mdr") == 0) {
- if (argc != 2)
+ if (argc == 2 || (argc == 0 && last_addr != 0))
+ valid = raw = 1;
+ else
return KDB_ARGCOUNT;
- valid = 1;
} else if (isdigit(argv[0][2])) {
bytesperword = (int)(argv[0][2] - '0');
if (bytesperword == 0) {
@@ -1611,7 +1613,10 @@ static int kdb_md(int argc, const char **argv)
radix = last_radix;
bytesperword = last_bytesperword;
repeat = last_repeat;
- mdcount = ((repeat * bytesperword) + 15) / 16;
+ if (raw)
+ mdcount = repeat;
+ else
+ mdcount = ((repeat * bytesperword) + 15) / 16;
}
if (argc) {
@@ -1628,7 +1633,10 @@ static int kdb_md(int argc, const char **argv)
diag = kdbgetularg(argv[nextarg], &val);
if (!diag) {
mdcount = (int) val;
- repeat = mdcount * 16 / bytesperword;
+ if (raw)
+ repeat = mdcount;
+ else
+ repeat = mdcount * 16 / bytesperword;
}
}
if (argc >= nextarg+1) {
@@ -1638,8 +1646,15 @@ static int kdb_md(int argc, const char **argv)
}
}
- if (strcmp(argv[0], "mdr") == 0)
- return kdb_mdr(addr, mdcount);
+ if (strcmp(argv[0], "mdr") == 0) {
+ int ret;
+ last_addr = addr;
+ ret = kdb_mdr(addr, mdcount);
+ last_addr += mdcount;
+ last_repeat = mdcount;
+ last_bytesperword = bytesperword; // to make REPEAT happy
+ return ret;
+ }
switch (radix) {
case 10:
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 75014d7f4568..533e04e75a9c 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -83,7 +83,7 @@ typedef struct __ksymtab {
unsigned long sym_start;
unsigned long sym_end;
} kdb_symtab_t;
-extern int kallsyms_symbol_next(char *prefix_name, int flag);
+extern int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size);
extern int kallsyms_symbol_complete(char *prefix_name, int max_len);
/* Exported Symbols for kernel loadable modules to use. */
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index d35cc2d3a4cc..61cd704a21c8 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -129,13 +129,13 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab)
}
if (i >= ARRAY_SIZE(kdb_name_table)) {
debug_kfree(kdb_name_table[0]);
- memcpy(kdb_name_table, kdb_name_table+1,
+ memmove(kdb_name_table, kdb_name_table+1,
sizeof(kdb_name_table[0]) *
(ARRAY_SIZE(kdb_name_table)-1));
} else {
debug_kfree(knt1);
knt1 = kdb_name_table[i];
- memcpy(kdb_name_table+i, kdb_name_table+i+1,
+ memmove(kdb_name_table+i, kdb_name_table+i+1,
sizeof(kdb_name_table[0]) *
(ARRAY_SIZE(kdb_name_table)-i-1));
}
@@ -221,11 +221,13 @@ int kallsyms_symbol_complete(char *prefix_name, int max_len)
* Parameters:
* prefix_name prefix of a symbol name to lookup
* flag 0 means search from the head, 1 means continue search.
+ * buf_size maximum length that can be written to prefix_name
+ * buffer
* Returns:
* 1 if a symbol matches the given prefix.
* 0 if no string found
*/
-int kallsyms_symbol_next(char *prefix_name, int flag)
+int kallsyms_symbol_next(char *prefix_name, int flag, int buf_size)
{
int prefix_len = strlen(prefix_name);
static loff_t pos;
@@ -235,10 +237,8 @@ int kallsyms_symbol_next(char *prefix_name, int flag)
pos = 0;
while ((name = kdb_walk_kallsyms(&pos))) {
- if (strncmp(name, prefix_name, prefix_len) == 0) {
- strncpy(prefix_name, name, strlen(name)+1);
- return 1;
- }
+ if (!strncmp(name, prefix_name, prefix_len))
+ return strscpy(prefix_name, name, buf_size);
}
return 0;
}
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 9c418002b8c1..75f835d353db 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -107,14 +107,8 @@ int get_callchain_buffers(void)
goto exit;
}
- if (count > 1) {
- /* If the allocation failed, give up */
- if (!callchain_cpus_entries)
- err = -ENOMEM;
- goto exit;
- }
-
- err = alloc_callchain_buffers();
+ if (count == 1)
+ err = alloc_callchain_buffers();
exit:
if (err)
atomic_dec(&nr_callchain_events);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bc6371b0e4fb..fbdc21cab957 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -175,8 +175,13 @@ static struct srcu_struct pmus_srcu;
* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
+ * 3 - disallow all unpriv perf event use
*/
+#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT
+int sysctl_perf_event_paranoid __read_mostly = 3;
+#else
int sysctl_perf_event_paranoid __read_mostly = 1;
+#endif
/* Minimum for 512 kiB + 1 user control page */
int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
@@ -229,7 +234,7 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
- int ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret || !write)
return ret;
@@ -419,9 +424,15 @@ static inline void __update_cgrp_time(struct perf_cgroup *cgrp)
static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx)
{
- struct perf_cgroup *cgrp_out = cpuctx->cgrp;
- if (cgrp_out)
- __update_cgrp_time(cgrp_out);
+ struct perf_cgroup *cgrp = cpuctx->cgrp;
+ struct cgroup_subsys_state *css;
+
+ if (cgrp) {
+ for (css = &cgrp->css; css; css = css->parent) {
+ cgrp = container_of(css, struct perf_cgroup, css);
+ __update_cgrp_time(cgrp);
+ }
+ }
}
static inline void update_cgrp_time_from_event(struct perf_event *event)
@@ -449,6 +460,7 @@ perf_cgroup_set_timestamp(struct task_struct *task,
{
struct perf_cgroup *cgrp;
struct perf_cgroup_info *info;
+ struct cgroup_subsys_state *css;
/*
* ctx->lock held by caller
@@ -459,8 +471,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
return;
cgrp = perf_cgroup_from_task(task, ctx);
- info = this_cpu_ptr(cgrp->info);
- info->timestamp = ctx->timestamp;
+
+ for (css = &cgrp->css; css; css = css->parent) {
+ cgrp = container_of(css, struct perf_cgroup, css);
+ info = this_cpu_ptr(cgrp->info);
+ info->timestamp = ctx->timestamp;
+ }
}
#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */
@@ -5271,9 +5287,6 @@ static void perf_output_read_one(struct perf_output_handle *handle,
__output_copy(handle, values, n * sizeof(u64));
}
-/*
- * XXX PERF_FORMAT_GROUP vs inherited events seems difficult.
- */
static void perf_output_read_group(struct perf_output_handle *handle,
struct perf_event *event,
u64 enabled, u64 running)
@@ -5291,7 +5304,8 @@ static void perf_output_read_group(struct perf_output_handle *handle,
if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
values[n++] = running;
- if (leader != event)
+ if ((leader != event) &&
+ (leader->state == PERF_EVENT_STATE_ACTIVE))
leader->pmu->read(leader);
values[n++] = perf_event_count(leader);
@@ -5318,6 +5332,13 @@ static void perf_output_read_group(struct perf_output_handle *handle,
#define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
PERF_FORMAT_TOTAL_TIME_RUNNING)
+/*
+ * XXX PERF_SAMPLE_READ vs inherited events seems difficult.
+ *
+ * The problem is that its both hard and excessively expensive to iterate the
+ * child list, not to mention that its impossible to IPI the children running
+ * on another CPU, from interrupt/NMI context.
+ */
static void perf_output_read(struct perf_output_handle *handle,
struct perf_event *event)
{
@@ -5982,6 +6003,7 @@ static void perf_event_mmap_output(struct perf_event *event,
struct perf_output_handle handle;
struct perf_sample_data sample;
int size = mmap_event->event_id.header.size;
+ u32 type = mmap_event->event_id.header.type;
int ret;
if (!perf_event_mmap_match(event, data))
@@ -6025,6 +6047,7 @@ static void perf_event_mmap_output(struct perf_event *event,
perf_output_end(&handle);
out:
mmap_event->event_id.header.size = size;
+ mmap_event->event_id.header.type = type;
}
static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
@@ -6039,6 +6062,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
char *buf = NULL;
char *name;
+ if (vma->vm_flags & VM_READ)
+ prot |= PROT_READ;
+ if (vma->vm_flags & VM_WRITE)
+ prot |= PROT_WRITE;
+ if (vma->vm_flags & VM_EXEC)
+ prot |= PROT_EXEC;
+
+ if (vma->vm_flags & VM_MAYSHARE)
+ flags = MAP_SHARED;
+ else
+ flags = MAP_PRIVATE;
+
+ if (vma->vm_flags & VM_DENYWRITE)
+ flags |= MAP_DENYWRITE;
+ if (vma->vm_flags & VM_MAYEXEC)
+ flags |= MAP_EXECUTABLE;
+ if (vma->vm_flags & VM_LOCKED)
+ flags |= MAP_LOCKED;
+ if (vma->vm_flags & VM_HUGETLB)
+ flags |= MAP_HUGETLB;
+
if (file) {
struct inode *inode;
dev_t dev;
@@ -6065,27 +6109,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
maj = MAJOR(dev);
min = MINOR(dev);
- if (vma->vm_flags & VM_READ)
- prot |= PROT_READ;
- if (vma->vm_flags & VM_WRITE)
- prot |= PROT_WRITE;
- if (vma->vm_flags & VM_EXEC)
- prot |= PROT_EXEC;
-
- if (vma->vm_flags & VM_MAYSHARE)
- flags = MAP_SHARED;
- else
- flags = MAP_PRIVATE;
-
- if (vma->vm_flags & VM_DENYWRITE)
- flags |= MAP_DENYWRITE;
- if (vma->vm_flags & VM_MAYEXEC)
- flags |= MAP_EXECUTABLE;
- if (vma->vm_flags & VM_LOCKED)
- flags |= MAP_LOCKED;
- if (vma->vm_flags & VM_HUGETLB)
- flags |= MAP_HUGETLB;
-
goto got_name;
} else {
if (vma->vm_ops && vma->vm_ops->name) {
@@ -7002,6 +7025,8 @@ void perf_tp_event(u64 addr, u64 count, void *record, int entry_size,
goto unlock;
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
+ if (event->cpu != smp_processor_id())
+ continue;
if (event->attr.type != PERF_TYPE_TRACEPOINT)
continue;
if (event->attr.config != entry->type)
@@ -7108,6 +7133,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd)
}
event->tp_event->prog = prog;
+ event->tp_event->bpf_prog_owner = event;
return 0;
}
@@ -7120,9 +7146,9 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
return;
prog = event->tp_event->prog;
- if (prog) {
+ if (prog && event->tp_event->bpf_prog_owner == event) {
event->tp_event->prog = NULL;
- bpf_prog_put_rcu(prog);
+ bpf_prog_put(prog);
}
}
@@ -7957,9 +7983,10 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
local64_set(&hwc->period_left, hwc->sample_period);
/*
- * we currently do not support PERF_FORMAT_GROUP on inherited events
+ * We currently do not support PERF_SAMPLE_READ on inherited events.
+ * See perf_output_read().
*/
- if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP))
+ if (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))
goto err_ns;
if (!has_branch_stack(event))
@@ -8127,9 +8154,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
* __u16 sample size limit.
*/
if (attr->sample_stack_user >= USHRT_MAX)
- ret = -EINVAL;
+ return -EINVAL;
else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
- ret = -EINVAL;
+ return -EINVAL;
}
if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
@@ -8250,6 +8277,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id)
return 0;
}
+/*
+ * Variation on perf_event_ctx_lock_nested(), except we take two context
+ * mutexes.
+ */
+static struct perf_event_context *
+__perf_event_ctx_lock_double(struct perf_event *group_leader,
+ struct perf_event_context *ctx)
+{
+ struct perf_event_context *gctx;
+
+again:
+ rcu_read_lock();
+ gctx = READ_ONCE(group_leader->ctx);
+ if (!atomic_inc_not_zero(&gctx->refcount)) {
+ rcu_read_unlock();
+ goto again;
+ }
+ rcu_read_unlock();
+
+ mutex_lock_double(&gctx->mutex, &ctx->mutex);
+
+ if (group_leader->ctx != gctx) {
+ mutex_unlock(&ctx->mutex);
+ mutex_unlock(&gctx->mutex);
+ put_ctx(gctx);
+ goto again;
+ }
+
+ return gctx;
+}
+
/**
* sys_perf_event_open - open a performance event, associate it to a task/cpu
*
@@ -8280,6 +8338,9 @@ SYSCALL_DEFINE5(perf_event_open,
if (flags & ~PERF_FLAG_ALL)
return -EINVAL;
+ if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
err = perf_copy_attr(attr_uptr, &attr);
if (err)
return err;
@@ -8442,28 +8503,27 @@ SYSCALL_DEFINE5(perf_event_open,
goto err_context;
/*
- * Do not allow to attach to a group in a different
- * task or CPU context:
+ * Make sure we're both events for the same CPU;
+ * grouping events for different CPUs is broken; since
+ * you can never concurrently schedule them anyhow.
*/
- if (move_group) {
- /*
- * Make sure we're both on the same task, or both
- * per-cpu events.
- */
- if (group_leader->ctx->task != ctx->task)
- goto err_context;
+ if (group_leader->cpu != event->cpu)
+ goto err_context;
- /*
- * Make sure we're both events for the same CPU;
- * grouping events for different CPUs is broken; since
- * you can never concurrently schedule them anyhow.
- */
- if (group_leader->cpu != event->cpu)
- goto err_context;
- } else {
- if (group_leader->ctx != ctx)
- goto err_context;
- }
+ /*
+ * Make sure we're both on the same task, or both
+ * per-CPU events.
+ */
+ if (group_leader->ctx->task != ctx->task)
+ goto err_context;
+
+ /*
+ * Do not allow to attach to a group in a different task
+ * or CPU context. If we're moving SW events, we'll fix
+ * this up later, so allow that.
+ */
+ if (!move_group && group_leader->ctx != ctx)
+ goto err_context;
/*
* Only a group leader can be exclusive or pinned
@@ -8482,12 +8542,31 @@ SYSCALL_DEFINE5(perf_event_open,
f_flags);
if (IS_ERR(event_file)) {
err = PTR_ERR(event_file);
+ event_file = NULL;
goto err_context;
}
if (move_group) {
- gctx = group_leader->ctx;
- mutex_lock_double(&gctx->mutex, &ctx->mutex);
+ gctx = __perf_event_ctx_lock_double(group_leader, ctx);
+
+ /*
+ * Check if we raced against another sys_perf_event_open() call
+ * moving the software group underneath us.
+ */
+ if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) {
+ /*
+ * If someone moved the group out from under us, check
+ * if this new event wound up on the same ctx, if so
+ * its the regular !move_group case, otherwise fail.
+ */
+ if (gctx != ctx) {
+ err = -EINVAL;
+ goto err_locked;
+ } else {
+ perf_event_ctx_unlock(group_leader, gctx);
+ move_group = 0;
+ }
+ }
} else {
mutex_lock(&ctx->mutex);
}
@@ -8582,7 +8661,7 @@ SYSCALL_DEFINE5(perf_event_open,
perf_unpin_context(ctx);
if (move_group)
- mutex_unlock(&gctx->mutex);
+ perf_event_ctx_unlock(group_leader, gctx);
mutex_unlock(&ctx->mutex);
if (task) {
@@ -8610,7 +8689,7 @@ SYSCALL_DEFINE5(perf_event_open,
err_locked:
if (move_group)
- mutex_unlock(&gctx->mutex);
+ perf_event_ctx_unlock(group_leader, gctx);
mutex_unlock(&ctx->mutex);
/* err_file: */
fput(event_file);
@@ -9230,7 +9309,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
ret = inherit_task_group(event, parent, parent_ctx,
child, ctxn, &inherited_all);
if (ret)
- break;
+ goto out_unlock;
}
/*
@@ -9246,7 +9325,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
ret = inherit_task_group(event, parent, parent_ctx,
child, ctxn, &inherited_all);
if (ret)
- break;
+ goto out_unlock;
}
raw_spin_lock_irqsave(&parent_ctx->lock, flags);
@@ -9274,6 +9353,7 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
}
raw_spin_unlock_irqrestore(&parent_ctx->lock, flags);
+out_unlock:
mutex_unlock(&parent_ctx->mutex);
perf_unpin_context(parent_ctx);
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 92ce5f4ccc26..a27245fdcd81 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -427,16 +427,9 @@ EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
* modify_user_hw_breakpoint - modify a user-space hardware breakpoint
* @bp: the breakpoint structure to modify
* @attr: new breakpoint attributes
- * @triggered: callback to trigger when we hit the breakpoint
- * @tsk: pointer to 'task_struct' of the process to which the address belongs
*/
int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
{
- u64 old_addr = bp->attr.bp_addr;
- u64 old_len = bp->attr.bp_len;
- int old_type = bp->attr.bp_type;
- int err = 0;
-
/*
* modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
* will not be possible to raise IPIs that invoke __perf_event_disable.
@@ -451,27 +444,18 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
bp->attr.bp_addr = attr->bp_addr;
bp->attr.bp_type = attr->bp_type;
bp->attr.bp_len = attr->bp_len;
+ bp->attr.disabled = 1;
- if (attr->disabled)
- goto end;
-
- err = validate_hw_breakpoint(bp);
- if (!err)
- perf_event_enable(bp);
+ if (!attr->disabled) {
+ int err = validate_hw_breakpoint(bp);
- if (err) {
- bp->attr.bp_addr = old_addr;
- bp->attr.bp_type = old_type;
- bp->attr.bp_len = old_len;
- if (!bp->attr.disabled)
- perf_event_enable(bp);
+ if (err)
+ return err;
- return err;
+ perf_event_enable(bp);
+ bp->attr.disabled = 0;
}
-end:
- bp->attr.disabled = attr->disabled;
-
return 0;
}
EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 014b69528194..7324d83d6bd8 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/circ_buf.h>
#include <linux/poll.h>
+#include <linux/nospec.h>
#include "internal.h"
@@ -288,6 +289,13 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
goto err;
/*
+ * If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
+ * the aux buffer is in perf_mmap_close(), about to get freed.
+ */
+ if (!atomic_read(&rb->aux_mmap_count))
+ goto err;
+
+ /*
* Nesting is not supported for AUX area, make sure nested
* writers are caught early
*/
@@ -467,6 +475,25 @@ static void rb_free_aux_page(struct ring_buffer *rb, int idx)
__free_page(page);
}
+static void __rb_free_aux(struct ring_buffer *rb)
+{
+ int pg;
+
+ if (rb->aux_priv) {
+ rb->free_aux(rb->aux_priv);
+ rb->free_aux = NULL;
+ rb->aux_priv = NULL;
+ }
+
+ if (rb->aux_nr_pages) {
+ for (pg = 0; pg < rb->aux_nr_pages; pg++)
+ rb_free_aux_page(rb, pg);
+
+ kfree(rb->aux_pages);
+ rb->aux_nr_pages = 0;
+ }
+}
+
int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
pgoff_t pgoff, int nr_pages, long watermark, int flags)
{
@@ -555,30 +582,11 @@ out:
if (!ret)
rb->aux_pgoff = pgoff;
else
- rb_free_aux(rb);
+ __rb_free_aux(rb);
return ret;
}
-static void __rb_free_aux(struct ring_buffer *rb)
-{
- int pg;
-
- if (rb->aux_priv) {
- rb->free_aux(rb->aux_priv);
- rb->free_aux = NULL;
- rb->aux_priv = NULL;
- }
-
- if (rb->aux_nr_pages) {
- for (pg = 0; pg < rb->aux_nr_pages; pg++)
- rb_free_aux_page(rb, pg);
-
- kfree(rb->aux_pages);
- rb->aux_nr_pages = 0;
- }
-}
-
void rb_free_aux(struct ring_buffer *rb)
{
if (atomic_dec_and_test(&rb->aux_refcount))
@@ -636,6 +644,9 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
size = sizeof(struct ring_buffer);
size += nr_pages * sizeof(void *);
+ if (order_base_2(size) >= PAGE_SHIFT+MAX_ORDER)
+ goto fail;
+
rb = kzalloc(size, GFP_KERNEL);
if (!rb)
goto fail;
@@ -779,8 +790,10 @@ perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff)
return NULL;
/* AUX space */
- if (pgoff >= rb->aux_pgoff)
- return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]);
+ if (pgoff >= rb->aux_pgoff) {
+ int aux_pgoff = array_index_nospec(pgoff - rb->aux_pgoff, rb->aux_nr_pages);
+ return virt_to_page(rb->aux_pages[aux_pgoff]);
+ }
}
return __perf_mmap_to_page(rb, pgoff);
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index da0c09ff6112..aad43c88a668 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -299,7 +299,7 @@ int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
retry:
/* Read the page with vaddr into memory */
- ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
+ ret = get_user_pages(NULL, mm, vaddr, 1, FOLL_FORCE, &old_page, &vma);
if (ret <= 0)
return ret;
@@ -606,7 +606,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
BUG_ON((uprobe->offset & ~PAGE_MASK) +
UPROBE_SWBP_INSN_SIZE > PAGE_SIZE);
- smp_wmb(); /* pairs with rmb() in find_active_uprobe() */
+ smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */
set_bit(UPROBE_COPY_INSN, &uprobe->flags);
out:
@@ -1700,7 +1700,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
if (likely(result == 0))
goto out;
- result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
+ result = get_user_pages(NULL, mm, vaddr, 1, FOLL_FORCE, &page, NULL);
if (result < 0)
return result;
@@ -1892,10 +1892,18 @@ static void handle_swbp(struct pt_regs *regs)
* After we hit the bp, _unregister + _register can install the
* new and not-yet-analyzed uprobe at the same address, restart.
*/
- smp_rmb(); /* pairs with wmb() in install_breakpoint() */
if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags)))
goto out;
+ /*
+ * Pairs with the smp_wmb() in prepare_uprobe().
+ *
+ * Guarantees that if we see the UPROBE_COPY_INSN bit set, then
+ * we must also see the stores to &uprobe->arch performed by the
+ * prepare_uprobe() call.
+ */
+ smp_rmb();
+
/* Tracing handlers use ->utask to communicate with fetch methods */
if (!get_utask())
goto out;
diff --git a/kernel/exit.c b/kernel/exit.c
index ffba5df4abd5..6e8ab67325a7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -53,6 +53,9 @@
#include <linux/oom.h>
#include <linux/writeback.h>
#include <linux/shm.h>
+#include <linux/kcov.h>
+
+#include "sched/tune.h"
#include <asm/uaccess.h>
#include <asm/unistd.h>
@@ -450,12 +453,14 @@ static struct task_struct *find_alive_thread(struct task_struct *p)
return NULL;
}
-static struct task_struct *find_child_reaper(struct task_struct *father)
+static struct task_struct *find_child_reaper(struct task_struct *father,
+ struct list_head *dead)
__releases(&tasklist_lock)
__acquires(&tasklist_lock)
{
struct pid_namespace *pid_ns = task_active_pid_ns(father);
struct task_struct *reaper = pid_ns->child_reaper;
+ struct task_struct *p, *n;
if (likely(reaper != father))
return reaper;
@@ -471,6 +476,12 @@ static struct task_struct *find_child_reaper(struct task_struct *father)
panic("Attempted to kill init! exitcode=0x%08x\n",
father->signal->group_exit_code ?: father->exit_code);
}
+
+ list_for_each_entry_safe(p, n, dead, ptrace_entry) {
+ list_del_init(&p->ptrace_entry);
+ release_task(p);
+ }
+
zap_pid_ns_processes(pid_ns);
write_lock_irq(&tasklist_lock);
@@ -557,7 +568,7 @@ static void forget_original_parent(struct task_struct *father,
exit_ptrace(father, dead);
/* Can drop and reacquire tasklist_lock */
- reaper = find_child_reaper(father);
+ reaper = find_child_reaper(father, dead);
if (list_empty(&father->children))
return;
@@ -657,6 +668,7 @@ void do_exit(long code)
TASKS_RCU(int tasks_rcu_i);
profile_task_exit(tsk);
+ kcov_task_exit(tsk);
WARN_ON(blk_needs_flush_plug(tsk));
@@ -699,6 +711,9 @@ void do_exit(long code)
}
exit_signals(tsk); /* sets PF_EXITING */
+
+ schedtune_exit_task(tsk);
+
/*
* tsk->flags are checked in the futex code to protect against
* an exiting task cleaning up the robust pi futexes.
@@ -746,7 +761,7 @@ void do_exit(long code)
disassociate_ctty(1);
exit_task_namespaces(tsk);
exit_task_work(tsk);
- exit_thread();
+ exit_thread(tsk);
/*
* Flush inherited counters to the parent - before the parent
@@ -1608,6 +1623,10 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
__WNOTHREAD|__WCLONE|__WALL))
return -EINVAL;
+ /* -INT_MIN is not defined */
+ if (upid == INT_MIN)
+ return -ESRCH;
+
if (upid == -1)
type = PIDTYPE_MAX;
else if (upid < 0) {
diff --git a/kernel/extable.c b/kernel/extable.c
index e820ccee9846..4f06fc34313f 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -66,7 +66,7 @@ static inline int init_kernel_text(unsigned long addr)
return 0;
}
-int core_kernel_text(unsigned long addr)
+int notrace core_kernel_text(unsigned long addr)
{
if (addr >= (unsigned long)_stext &&
addr < (unsigned long)_etext)
diff --git a/kernel/fork.c b/kernel/fork.c
index 7161ebe67cbb..c6e26e433445 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -58,6 +58,7 @@
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/freezer.h>
+#include <linux/kaiser.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
#include <linux/random.h>
@@ -75,6 +76,8 @@
#include <linux/aio.h>
#include <linux/compiler.h>
#include <linux/sysctl.h>
+#include <linux/kcov.h>
+#include <linux/cpufreq_times.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
@@ -147,18 +150,18 @@ static inline void free_task_struct(struct task_struct *tsk)
}
#endif
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
{
}
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
* kmemcache based allocator.
*/
# if THREAD_SIZE >= PAGE_SIZE
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
@@ -167,29 +170,32 @@ static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
return page ? page_address(page) : NULL;
}
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(unsigned long *stack)
{
- free_kmem_pages((unsigned long)ti, THREAD_SIZE_ORDER);
+ struct page *page = virt_to_page(stack);
+
+ kaiser_unmap_thread_stack(stack);
+ __free_kmem_pages(page, THREAD_SIZE_ORDER);
}
# else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+ return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
}
-static void free_thread_info(struct thread_info *ti)
+static void free_thread_stack(unsigned long *stack)
{
- kmem_cache_free(thread_info_cache, ti);
+ kmem_cache_free(thread_stack_cache, stack);
}
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
{
- thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+ thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
THREAD_SIZE, 0, NULL);
- BUG_ON(thread_info_cache == NULL);
+ BUG_ON(thread_stack_cache == NULL);
}
# endif
#endif
@@ -212,18 +218,19 @@ struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
-static void account_kernel_stack(struct thread_info *ti, int account)
+static void account_kernel_stack(unsigned long *stack, int account)
{
- struct zone *zone = page_zone(virt_to_page(ti));
+ struct zone *zone = page_zone(virt_to_page(stack));
mod_zone_page_state(zone, NR_KERNEL_STACK, account);
}
void free_task(struct task_struct *tsk)
{
+ cpufreq_task_times_exit(tsk);
account_kernel_stack(tsk->stack, -1);
- arch_release_thread_info(tsk->stack);
- free_thread_info(tsk->stack);
+ arch_release_thread_stack(tsk->stack);
+ free_thread_stack(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
put_seccomp_filter(tsk);
@@ -331,26 +338,31 @@ void set_task_stack_end_magic(struct task_struct *tsk)
*stackend = STACK_END_MAGIC; /* for overflow detection */
}
-static struct task_struct *dup_task_struct(struct task_struct *orig)
+static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
- struct thread_info *ti;
- int node = tsk_fork_get_node(orig);
+ unsigned long *stack;
int err;
+ if (node == NUMA_NO_NODE)
+ node = tsk_fork_get_node(orig);
tsk = alloc_task_struct_node(node);
if (!tsk)
return NULL;
- ti = alloc_thread_info_node(tsk, node);
- if (!ti)
+ stack = alloc_thread_stack_node(tsk, node);
+ if (!stack)
goto free_tsk;
err = arch_dup_task_struct(tsk, orig);
if (err)
- goto free_ti;
+ goto free_stack;
+
+ tsk->stack = stack;
- tsk->stack = ti;
+ err = kaiser_map_thread_stack(tsk->stack);
+ if (err)
+ goto free_stack;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
@@ -367,7 +379,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
set_task_stack_end_magic(tsk);
#ifdef CONFIG_CC_STACKPROTECTOR
- tsk->stack_canary = get_random_int();
+ tsk->stack_canary = get_random_long();
#endif
/*
@@ -382,12 +394,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
- account_kernel_stack(ti, 1);
+ account_kernel_stack(stack, 1);
+
+ kcov_task_init(tsk);
return tsk;
-free_ti:
- free_thread_info(ti);
+free_stack:
+ free_thread_stack(stack);
free_tsk:
free_task_struct(tsk);
return NULL;
@@ -585,7 +599,8 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
#endif
}
-static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
+static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
+ struct user_namespace *user_ns)
{
mm->mmap = NULL;
mm->mm_rb = RB_ROOT;
@@ -625,6 +640,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
if (init_new_context(p, mm))
goto fail_nocontext;
+ mm->user_ns = get_user_ns(user_ns);
return mm;
fail_nocontext:
@@ -670,7 +686,7 @@ struct mm_struct *mm_alloc(void)
return NULL;
memset(mm, 0, sizeof(*mm));
- return mm_init(mm, current);
+ return mm_init(mm, current, current_user_ns());
}
/*
@@ -685,10 +701,31 @@ void __mmdrop(struct mm_struct *mm)
destroy_context(mm);
mmu_notifier_mm_destroy(mm);
check_mm(mm);
+ put_user_ns(mm->user_ns);
free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);
+static inline void __mmput(struct mm_struct *mm)
+{
+ VM_BUG_ON(atomic_read(&mm->mm_users));
+
+ uprobe_clear_state(mm);
+ exit_aio(mm);
+ ksm_exit(mm);
+ khugepaged_exit(mm); /* must run before exit_mmap */
+ exit_mmap(mm);
+ set_mm_exe_file(mm, NULL);
+ if (!list_empty(&mm->mmlist)) {
+ spin_lock(&mmlist_lock);
+ list_del(&mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+ if (mm->binfmt)
+ module_put(mm->binfmt->module);
+ mmdrop(mm);
+}
+
/*
* Decrement the use count and release all resources for an mm.
*/
@@ -696,24 +733,24 @@ void mmput(struct mm_struct *mm)
{
might_sleep();
+ if (atomic_dec_and_test(&mm->mm_users))
+ __mmput(mm);
+}
+EXPORT_SYMBOL_GPL(mmput);
+
+static void mmput_async_fn(struct work_struct *work)
+{
+ struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
+ __mmput(mm);
+}
+
+void mmput_async(struct mm_struct *mm)
+{
if (atomic_dec_and_test(&mm->mm_users)) {
- uprobe_clear_state(mm);
- exit_aio(mm);
- ksm_exit(mm);
- khugepaged_exit(mm); /* must run before exit_mmap */
- exit_mmap(mm);
- set_mm_exe_file(mm, NULL);
- if (!list_empty(&mm->mmlist)) {
- spin_lock(&mmlist_lock);
- list_del(&mm->mmlist);
- spin_unlock(&mmlist_lock);
- }
- if (mm->binfmt)
- module_put(mm->binfmt->module);
- mmdrop(mm);
+ INIT_WORK(&mm->async_put_work, mmput_async_fn);
+ schedule_work(&mm->async_put_work);
}
}
-EXPORT_SYMBOL_GPL(mmput);
/**
* set_mm_exe_file - change a reference to the mm's executable file
@@ -942,7 +979,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
memcpy(mm, oldmm, sizeof(*mm));
- if (!mm_init(mm, tsk))
+ if (!mm_init(mm, tsk, mm->user_ns))
goto fail_nomem;
err = dup_mmap(mm, oldmm);
@@ -1099,7 +1136,9 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
return -ENOMEM;
atomic_set(&sig->count, 1);
+ spin_lock_irq(&current->sighand->siglock);
memcpy(sig->action, current->sighand->action, sizeof(sig->action));
+ spin_unlock_irq(&current->sighand->siglock);
return 0;
}
@@ -1267,7 +1306,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
int __user *child_tidptr,
struct pid *pid,
int trace,
- unsigned long tls)
+ unsigned long tls,
+ int node)
{
int retval;
struct task_struct *p;
@@ -1320,10 +1360,24 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto fork_out;
retval = -ENOMEM;
- p = dup_task_struct(current);
+ p = dup_task_struct(current, node);
if (!p)
goto fork_out;
+ cpufreq_task_times_init(p);
+
+ /*
+ * This _must_ happen before we call free_task(), i.e. before we jump
+ * to any of the bad_fork_* labels. This is to avoid freeing
+ * p->set_child_tid which is (ab)used as a kthread's data pointer for
+ * kernel threads (PF_KTHREAD).
+ */
+ p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
+ /*
+ * Clear TID on mm_release()?
+ */
+ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
+
ftrace_graph_init_task(p);
rt_mutex_init_task(p);
@@ -1386,8 +1440,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
posix_cpu_timers_init(p);
- p->start_time = ktime_get_ns();
- p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
cgroup_fork(p);
@@ -1485,11 +1537,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
}
}
- p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
- /*
- * Clear TID on mm_release()?
- */
- p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL;
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
@@ -1553,6 +1600,17 @@ static struct task_struct *copy_process(unsigned long clone_flags,
goto bad_fork_free_pid;
/*
+ * From this point on we must avoid any synchronous user-space
+ * communication until we take the tasklist-lock. In particular, we do
+ * not want user-space to be able to predict the process start-time by
+ * stalling fork(2) after we recorded the start_time but before it is
+ * visible to the system.
+ */
+
+ p->start_time = ktime_get_ns();
+ p->real_start_time = ktime_get_boot_ns();
+
+ /*
* Make it visible to the rest of the system, but dont wake it up yet.
* Need tasklist lock for parent etc handling!
*/
@@ -1585,11 +1643,13 @@ static struct task_struct *copy_process(unsigned long clone_flags,
*/
recalc_sigpending();
if (signal_pending(current)) {
- spin_unlock(&current->sighand->siglock);
- write_unlock_irq(&tasklist_lock);
retval = -ERESTARTNOINTR;
goto bad_fork_cancel_cgroup;
}
+ if (unlikely(!(ns_of_pid(pid)->nr_hashed & PIDNS_HASH_ADDING))) {
+ retval = -ENOMEM;
+ goto bad_fork_cancel_cgroup;
+ }
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -1640,6 +1700,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
return p;
bad_fork_cancel_cgroup:
+ spin_unlock(&current->sighand->siglock);
+ write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p, cgrp_ss_priv);
bad_fork_free_pid:
threadgroup_change_end(current);
@@ -1696,7 +1758,8 @@ static inline void init_idle_pids(struct pid_link *links)
struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
- task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0);
+ task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+ cpu_to_node(cpu));
if (!IS_ERR(task)) {
init_idle_pids(task->pids);
init_idle(task, cpu);
@@ -1741,7 +1804,7 @@ long _do_fork(unsigned long clone_flags,
}
p = copy_process(clone_flags, stack_start, stack_size,
- child_tidptr, NULL, trace, tls);
+ child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
@@ -1750,6 +1813,8 @@ long _do_fork(unsigned long clone_flags,
struct completion vfork;
struct pid *pid;
+ cpufreq_task_times_alloc(p);
+
trace_sched_process_fork(current, p);
pid = get_task_pid(p, PIDTYPE_PID);
diff --git a/kernel/futex.c b/kernel/futex.c
index 9d8163afd87c..ec9df5ba040b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -470,6 +470,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
unsigned long address = (unsigned long)uaddr;
struct mm_struct *mm = current->mm;
struct page *page, *page_head;
+ struct address_space *mapping;
int err, ro = 0;
/*
@@ -555,7 +556,19 @@ again:
}
#endif
- lock_page(page_head);
+ /*
+ * The treatment of mapping from this point on is critical. The page
+ * lock protects many things but in this context the page lock
+ * stabilizes mapping, prevents inode freeing in the shared
+ * file-backed region case and guards against movement to swap cache.
+ *
+ * Strictly speaking the page lock is not needed in all cases being
+ * considered here and page lock forces unnecessarily serialization
+ * From this point on, mapping will be re-verified if necessary and
+ * page lock will be acquired only if it is unavoidable
+ */
+
+ mapping = READ_ONCE(page_head->mapping);
/*
* If page_head->mapping is NULL, then it cannot be a PageAnon
@@ -572,18 +585,31 @@ again:
* shmem_writepage move it from filecache to swapcache beneath us:
* an unlikely race, but we do need to retry for page_head->mapping.
*/
- if (!page_head->mapping) {
- int shmem_swizzled = PageSwapCache(page_head);
+ if (unlikely(!mapping)) {
+ int shmem_swizzled;
+
+ /*
+ * Page lock is required to identify which special case above
+ * applies. If this is really a shmem page then the page lock
+ * will prevent unexpected transitions.
+ */
+ lock_page(page);
+ shmem_swizzled = PageSwapCache(page) || page->mapping;
unlock_page(page_head);
put_page(page_head);
+
if (shmem_swizzled)
goto again;
+
return -EFAULT;
}
/*
* Private mappings are handled in a simple way.
*
+ * If the futex key is stored on an anonymous page, then the associated
+ * object is the mm which is implicitly pinned by the calling process.
+ *
* 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.
@@ -601,16 +627,75 @@ again:
key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
key->private.mm = mm;
key->private.address = address;
+
+ get_futex_key_refs(key); /* implies smp_mb(); (B) */
+
} else {
+ struct inode *inode;
+
+ /*
+ * The associated futex object in this case is the inode and
+ * the page->mapping must be traversed. Ordinarily this should
+ * be stabilised under page lock but it's not strictly
+ * necessary in this case as we just want to pin the inode, not
+ * update the radix tree or anything like that.
+ *
+ * The RCU read lock is taken as the inode is finally freed
+ * under RCU. If the mapping still matches expectations then the
+ * mapping->host can be safely accessed as being a valid inode.
+ */
+ rcu_read_lock();
+
+ if (READ_ONCE(page_head->mapping) != mapping) {
+ rcu_read_unlock();
+ put_page(page_head);
+
+ goto again;
+ }
+
+ inode = READ_ONCE(mapping->host);
+ if (!inode) {
+ rcu_read_unlock();
+ put_page(page_head);
+
+ goto again;
+ }
+
+ /*
+ * Take a reference unless it is about to be freed. Previously
+ * this reference was taken by ihold under the page lock
+ * pinning the inode in place so i_lock was unnecessary. The
+ * only way for this check to fail is if the inode was
+ * truncated in parallel which is almost certainly an
+ * application bug. In such a case, just retry.
+ *
+ * We are not calling into get_futex_key_refs() in file-backed
+ * cases, therefore a successful atomic_inc return below will
+ * guarantee that get_futex_key() will still imply smp_mb(); (B).
+ */
+ if (!atomic_inc_not_zero(&inode->i_count)) {
+ rcu_read_unlock();
+ put_page(page_head);
+
+ goto again;
+ }
+
+ /* Should be impossible but lets be paranoid for now */
+ if (WARN_ON_ONCE(inode->i_mapping != mapping)) {
+ err = -EFAULT;
+ rcu_read_unlock();
+ iput(inode);
+
+ goto out;
+ }
+
key->both.offset |= FUT_OFF_INODE; /* inode-based key */
- key->shared.inode = page_head->mapping->host;
+ key->shared.inode = inode;
key->shared.pgoff = basepage_index(page);
+ rcu_read_unlock();
}
- get_futex_key_refs(key); /* implies MB (B) */
-
out:
- unlock_page(page_head);
put_page(page_head);
return err;
}
@@ -1368,6 +1453,45 @@ out:
return ret;
}
+static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
+{
+ unsigned int op = (encoded_op & 0x70000000) >> 28;
+ unsigned int cmp = (encoded_op & 0x0f000000) >> 24;
+ int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 11);
+ int cmparg = sign_extend32(encoded_op & 0x00000fff, 11);
+ int oldval, ret;
+
+ if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
+ if (oparg < 0 || oparg > 31)
+ return -EINVAL;
+ oparg = 1 << oparg;
+ }
+
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+ return -EFAULT;
+
+ ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr);
+ if (ret)
+ return ret;
+
+ switch (cmp) {
+ case FUTEX_OP_CMP_EQ:
+ return oldval == cmparg;
+ case FUTEX_OP_CMP_NE:
+ return oldval != cmparg;
+ case FUTEX_OP_CMP_LT:
+ return oldval < cmparg;
+ case FUTEX_OP_CMP_GE:
+ return oldval >= cmparg;
+ case FUTEX_OP_CMP_LE:
+ return oldval <= cmparg;
+ case FUTEX_OP_CMP_GT:
+ return oldval > cmparg;
+ default:
+ return -ENOSYS;
+ }
+}
+
/*
* Wake up all waiters hashed on the physical page that is mapped
* to this virtual address:
@@ -1621,6 +1745,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
struct futex_q *this, *next;
WAKE_Q(wake_q);
+ if (nr_wake < 0 || nr_requeue < 0)
+ return -EINVAL;
+
if (requeue_pi) {
/*
* Requeue PI only works on two distinct uaddrs. This
@@ -1939,8 +2066,12 @@ static int unqueue_me(struct futex_q *q)
/* In the common case we don't take the spinlock, which is nice. */
retry:
- lock_ptr = q->lock_ptr;
- barrier();
+ /*
+ * q->lock_ptr can change between this read and the following spin_lock.
+ * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and
+ * optimizing lock_ptr out of the logic below.
+ */
+ lock_ptr = READ_ONCE(q->lock_ptr);
if (lock_ptr != NULL) {
spin_lock(lock_ptr);
/*
@@ -2690,7 +2821,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
{
struct hrtimer_sleeper timeout, *to = NULL;
struct rt_mutex_waiter rt_waiter;
- struct rt_mutex *pi_mutex = NULL;
struct futex_hash_bucket *hb;
union futex_key key2 = FUTEX_KEY_INIT;
struct futex_q q = futex_q_init;
@@ -2774,6 +2904,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
if (q.pi_state && (q.pi_state->owner != current)) {
spin_lock(q.lock_ptr);
ret = fixup_pi_state_owner(uaddr2, &q, current);
+ if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
+ rt_mutex_unlock(&q.pi_state->pi_mutex);
/*
* Drop the reference to the pi state which
* the requeue_pi() code acquired for us.
@@ -2782,6 +2914,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
spin_unlock(q.lock_ptr);
}
} else {
+ struct rt_mutex *pi_mutex;
+
/*
* We have been woken up by futex_unlock_pi(), a timeout, or a
* signal. futex_unlock_pi() will not destroy the lock_ptr nor
@@ -2789,10 +2923,13 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
*/
WARN_ON(!q.pi_state);
pi_mutex = &q.pi_state->pi_mutex;
- ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
- debug_rt_mutex_free_waiter(&rt_waiter);
+ ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
spin_lock(q.lock_ptr);
+ if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+ ret = 0;
+
+ debug_rt_mutex_free_waiter(&rt_waiter);
/*
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
@@ -2805,18 +2942,19 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
if (res)
ret = (res < 0) ? res : 0;
+ /*
+ * If fixup_pi_state_owner() faulted and was unable to handle
+ * the fault, unlock the rt_mutex and return the fault to
+ * userspace.
+ */
+ if (ret && rt_mutex_owner(pi_mutex) == current)
+ rt_mutex_unlock(pi_mutex);
+
/* Unqueue and drop the lock. */
unqueue_me_pi(&q);
}
- /*
- * If fixup_pi_state_owner() faulted and was unable to handle the
- * fault, unlock the rt_mutex and return the fault to userspace.
- */
- if (ret == -EFAULT) {
- if (pi_mutex && rt_mutex_owner(pi_mutex) == current)
- rt_mutex_unlock(pi_mutex);
- } else if (ret == -EINTR) {
+ if (ret == -EINTR) {
/*
* We've already been requeued, but cannot restart by calling
* futex_lock_pi() directly. We could restart this syscall, but
@@ -2929,6 +3067,10 @@ int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
{
u32 uval, uninitialized_var(nval), mval;
+ /* Futex address must be 32bit aligned */
+ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
+ return -1;
+
retry:
if (get_user(uval, uaddr))
return -1;
@@ -3199,4 +3341,4 @@ static int __init futex_init(void)
return 0;
}
-__initcall(futex_init);
+core_initcall(futex_init);
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index c92e44855ddd..1276aabaab55 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -37,6 +37,7 @@ config ARCH_HAS_GCOV_PROFILE_ALL
config GCOV_PROFILE_ALL
bool "Profile entire Kernel"
+ depends on !COMPILE_TEST
depends on GCOV_KERNEL
depends on ARCH_HAS_GCOV_PROFILE_ALL
default n
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index 7080ae1eb6c1..f850e906564b 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -98,6 +98,12 @@ void __gcov_merge_icall_topn(gcov_type *counters, unsigned int n_counters)
}
EXPORT_SYMBOL(__gcov_merge_icall_topn);
+void __gcov_exit(void)
+{
+ /* Unused. */
+}
+EXPORT_SYMBOL(__gcov_exit);
+
/**
* gcov_enable_events - enable event reporting through gcov_event()
*
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index e25e92fb44fa..46a18e72bce6 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -18,7 +18,9 @@
#include <linux/vmalloc.h>
#include "gcov.h"
-#if __GNUC__ == 5 && __GNUC_MINOR__ >= 1
+#if (__GNUC__ >= 7)
+#define GCOV_COUNTERS 9
+#elif (__GNUC__ > 5) || (__GNUC__ == 5 && __GNUC_MINOR__ >= 1)
#define GCOV_COUNTERS 10
#elif __GNUC__ == 4 && __GNUC_MINOR__ >= 9
#define GCOV_COUNTERS 9
diff --git a/kernel/groups.c b/kernel/groups.c
index 74d431d25251..5ea9847f172f 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -101,7 +101,7 @@ static int groups_from_user(struct group_info *group_info,
}
/* a simple Shell sort */
-static void groups_sort(struct group_info *group_info)
+void groups_sort(struct group_info *group_info)
{
int base, max, stride;
int gidsetsize = group_info->ngroups;
@@ -128,6 +128,7 @@ static void groups_sort(struct group_info *group_info)
stride /= 3;
}
}
+EXPORT_SYMBOL(groups_sort);
/* a simple bsearch */
int groups_search(const struct group_info *group_info, kgid_t grp)
@@ -159,7 +160,6 @@ int groups_search(const struct group_info *group_info, kgid_t grp)
void set_groups(struct cred *new, struct group_info *group_info)
{
put_group_info(new->group_info);
- groups_sort(group_info);
get_group_info(group_info);
new->group_info = group_info;
}
@@ -243,6 +243,7 @@ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist)
return retval;
}
+ groups_sort(group_info);
retval = set_current_groups(group_info);
put_group_info(group_info);
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index e0f90c2b57aa..cc05b97ba569 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -30,7 +30,7 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
* is disabled during the critical section. It also controls the size of
* the RCU grace period. So it needs to be upper-bound.
*/
-#define HUNG_TASK_BATCHING 1024
+#define HUNG_TASK_LOCK_BREAK (HZ / 10)
/*
* Zero means infinite timeout - no checking done:
@@ -158,7 +158,7 @@ static bool rcu_lock_break(struct task_struct *g, struct task_struct *t)
static void check_hung_uninterruptible_tasks(unsigned long timeout)
{
int max_count = sysctl_hung_task_check_count;
- int batch_count = HUNG_TASK_BATCHING;
+ unsigned long last_break = jiffies;
struct task_struct *g, *t;
/*
@@ -172,10 +172,10 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
for_each_process_thread(g, t) {
if (!max_count--)
goto unlock;
- if (!--batch_count) {
- batch_count = HUNG_TASK_BATCHING;
+ if (time_after(jiffies, last_break + HUNG_TASK_LOCK_BREAK)) {
if (!rcu_lock_break(g, t))
goto unlock;
+ last_break = jiffies;
}
/* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */
if (t->state == TASK_UNINTERRUPTIBLE)
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 15206453b12a..67aafc2b249c 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -338,7 +338,6 @@ void handle_nested_irq(unsigned int irq)
raw_spin_lock_irq(&desc->lock);
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
- kstat_incr_irqs_this_cpu(desc);
action = desc->action;
if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
@@ -346,6 +345,7 @@ void handle_nested_irq(unsigned int irq)
goto out_unlock;
}
+ kstat_incr_irqs_this_cpu(desc);
irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
raw_spin_unlock_irq(&desc->lock);
@@ -412,13 +412,13 @@ void handle_simple_irq(struct irq_desc *desc)
goto out_unlock;
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
- kstat_incr_irqs_this_cpu(desc);
if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
desc->istate |= IRQS_PENDING;
goto out_unlock;
}
+ kstat_incr_irqs_this_cpu(desc);
handle_irq_event(desc);
out_unlock:
@@ -462,7 +462,6 @@ void handle_level_irq(struct irq_desc *desc)
goto out_unlock;
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
- kstat_incr_irqs_this_cpu(desc);
/*
* If its disabled or no action available
@@ -473,6 +472,7 @@ void handle_level_irq(struct irq_desc *desc)
goto out_unlock;
}
+ kstat_incr_irqs_this_cpu(desc);
handle_irq_event(desc);
cond_unmask_irq(desc);
@@ -532,7 +532,6 @@ void handle_fasteoi_irq(struct irq_desc *desc)
goto out;
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
- kstat_incr_irqs_this_cpu(desc);
/*
* If its disabled or no action available
@@ -544,6 +543,7 @@ void handle_fasteoi_irq(struct irq_desc *desc)
goto out;
}
+ kstat_incr_irqs_this_cpu(desc);
if (desc->istate & IRQS_ONESHOT)
mask_irq(desc);
@@ -810,8 +810,8 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle,
if (!desc)
return;
- __irq_do_set_handler(desc, handle, 1, NULL);
desc->irq_common_data.handler_data = data;
+ __irq_do_set_handler(desc, handle, 1, NULL);
irq_put_desc_busunlock(desc, flags);
}
@@ -1056,6 +1056,10 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on)
{
data = data->parent_data;
+
+ if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE)
+ return 0;
+
if (data->chip->irq_set_wake)
return data->chip->irq_set_wake(data, on);
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index abd286afbd27..a4775f3451b9 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -411,8 +411,29 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
}
EXPORT_SYMBOL_GPL(irq_map_generic_chip);
+static void irq_unmap_generic_chip(struct irq_domain *d, unsigned int virq)
+{
+ struct irq_data *data = irq_domain_get_irq_data(d, virq);
+ struct irq_domain_chip_generic *dgc = d->gc;
+ unsigned int hw_irq = data->hwirq;
+ struct irq_chip_generic *gc;
+ int irq_idx;
+
+ gc = irq_get_domain_generic_chip(d, hw_irq);
+ if (!gc)
+ return;
+
+ irq_idx = hw_irq % dgc->irqs_per_chip;
+
+ clear_bit(irq_idx, &gc->installed);
+ irq_domain_set_info(d, virq, hw_irq, &no_irq_chip, NULL, NULL, NULL,
+ NULL);
+
+}
+
struct irq_domain_ops irq_generic_chip_ops = {
.map = irq_map_generic_chip,
+ .unmap = irq_unmap_generic_chip,
.xlate = irq_domain_xlate_onetwocell,
};
EXPORT_SYMBOL_GPL(irq_generic_chip_ops);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 6ead200370da..92c7eb1aeded 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -319,8 +319,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
desc->affinity_notify = notify;
raw_spin_unlock_irqrestore(&desc->lock, flags);
- if (old_notify)
+ if (old_notify) {
+ cancel_work_sync(&old_notify->work);
kref_put(&old_notify->kref, old_notify->release);
+ }
return 0;
}
@@ -836,7 +838,7 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
* This code is triggered unconditionally. Check the affinity
* mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
*/
- if (desc->irq_common_data.affinity)
+ if (cpumask_available(desc->irq_common_data.affinity))
cpumask_copy(mask, desc->irq_common_data.affinity);
else
valid = false;
@@ -864,6 +866,9 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
local_bh_disable();
ret = action->thread_fn(action->irq, action->dev_id);
+ if (ret == IRQ_HANDLED)
+ atomic_inc(&desc->threads_handled);
+
irq_finalize_oneshot(desc, action);
local_bh_enable();
return ret;
@@ -880,6 +885,9 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
irqreturn_t ret;
ret = action->thread_fn(action->irq, action->dev_id);
+ if (ret == IRQ_HANDLED)
+ atomic_inc(&desc->threads_handled);
+
irq_finalize_oneshot(desc, action);
return ret;
}
@@ -957,8 +965,6 @@ static int irq_thread(void *data)
irq_thread_check_affinity(desc, action);
action_ret = handler_fn(desc, action);
- if (action_ret == IRQ_HANDLED)
- atomic_inc(&desc->threads_handled);
if (action_ret == IRQ_WAKE_THREAD)
irq_wake_secondary(desc, action);
@@ -1012,6 +1018,13 @@ static int irq_setup_forced_threading(struct irqaction *new)
if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
return 0;
+ /*
+ * No further action required for interrupts which are requested as
+ * threaded interrupts already
+ */
+ if (new->handler == irq_default_primary_handler)
+ return 0;
+
new->flags |= IRQF_ONESHOT;
/*
@@ -1019,7 +1032,7 @@ static int irq_setup_forced_threading(struct irqaction *new)
* thread handler. We force thread them as well by creating a
* secondary action.
*/
- if (new->handler != irq_default_primary_handler && new->thread_fn) {
+ if (new->handler && new->thread_fn) {
/* Allocate the secondary action */
new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!new->secondary)
@@ -1287,8 +1300,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
ret = __irq_set_trigger(desc,
new->flags & IRQF_TRIGGER_MASK);
- if (ret)
+ if (ret) {
+ irq_release_resources(desc);
goto out_mask;
+ }
}
desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 4b353e0be121..e863b2339174 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -138,6 +138,13 @@ void static_key_slow_dec_deferred(struct static_key_deferred *key)
}
EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
+void static_key_deferred_flush(struct static_key_deferred *key)
+{
+ STATIC_KEY_CHECK_USE();
+ flush_delayed_work(&key->work);
+}
+EXPORT_SYMBOL_GPL(static_key_deferred_flush);
+
void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
@@ -546,7 +553,7 @@ static __init int jump_label_test(void)
return 0;
}
-late_initcall(jump_label_test);
+early_initcall(jump_label_test);
#endif /* STATIC_KEYS_SELFTEST */
#endif /* HAVE_JUMP_LABEL */
diff --git a/kernel/kcov.c b/kernel/kcov.c
new file mode 100644
index 000000000000..5813e9375a93
--- /dev/null
+++ b/kernel/kcov.c
@@ -0,0 +1,431 @@
+#define pr_fmt(fmt) "kcov: " fmt
+
+#define DISABLE_BRANCH_PROFILING
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/preempt.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/kcov.h>
+#include <asm/setup.h>
+
+/* Number of 64-bit words written per one comparison: */
+#define KCOV_WORDS_PER_CMP 4
+
+/*
+ * kcov descriptor (one per opened debugfs file).
+ * State transitions of the descriptor:
+ * - initial state after open()
+ * - then there must be a single ioctl(KCOV_INIT_TRACE) call
+ * - then, mmap() call (several calls are allowed but not useful)
+ * - then, ioctl(KCOV_ENABLE, arg), where arg is
+ * KCOV_TRACE_PC - to trace only the PCs
+ * or
+ * KCOV_TRACE_CMP - to trace only the comparison operands
+ * - then, ioctl(KCOV_DISABLE) to disable the task.
+ * Enabling/disabling ioctls can be repeated (only one task a time allowed).
+ */
+struct kcov {
+ /*
+ * Reference counter. We keep one for:
+ * - opened file descriptor
+ * - task with enabled coverage (we can't unwire it from another task)
+ */
+ atomic_t refcount;
+ /* The lock protects mode, size, area and t. */
+ spinlock_t lock;
+ enum kcov_mode mode;
+ /* Size of arena (in long's for KCOV_MODE_TRACE). */
+ unsigned size;
+ /* Coverage buffer shared with user space. */
+ void *area;
+ /* Task for which we collect coverage, or NULL. */
+ struct task_struct *t;
+};
+
+static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
+{
+ enum kcov_mode mode;
+
+ /*
+ * We are interested in code coverage as a function of a syscall inputs,
+ * so we ignore code executed in interrupts.
+ */
+ if (!in_task())
+ return false;
+ mode = READ_ONCE(t->kcov_mode);
+ /*
+ * There is some code that runs in interrupts but for which
+ * in_interrupt() returns false (e.g. preempt_schedule_irq()).
+ * READ_ONCE()/barrier() effectively provides load-acquire wrt
+ * interrupts, there are paired barrier()/WRITE_ONCE() in
+ * kcov_ioctl_locked().
+ */
+ barrier();
+ return mode == needed_mode;
+}
+
+static unsigned long canonicalize_ip(unsigned long ip)
+{
+#ifdef CONFIG_RANDOMIZE_BASE
+ ip -= kaslr_offset();
+#endif
+ return ip;
+}
+
+/*
+ * Entry point from instrumented code.
+ * This is called once per basic-block/edge.
+ */
+void notrace __sanitizer_cov_trace_pc(void)
+{
+ struct task_struct *t;
+ unsigned long *area;
+ unsigned long ip = canonicalize_ip(_RET_IP_);
+ unsigned long pos;
+
+ t = current;
+ if (!check_kcov_mode(KCOV_MODE_TRACE_PC, t))
+ return;
+
+ area = t->kcov_area;
+ /* The first 64-bit word is the number of subsequent PCs. */
+ pos = READ_ONCE(area[0]) + 1;
+ if (likely(pos < t->kcov_size)) {
+ area[pos] = ip;
+ WRITE_ONCE(area[0], pos);
+ }
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_pc);
+
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+static void write_comp_data(u64 type, u64 arg1, u64 arg2, u64 ip)
+{
+ struct task_struct *t;
+ u64 *area;
+ u64 count, start_index, end_pos, max_pos;
+
+ t = current;
+ if (!check_kcov_mode(KCOV_MODE_TRACE_CMP, t))
+ return;
+
+ ip = canonicalize_ip(ip);
+
+ /*
+ * We write all comparison arguments and types as u64.
+ * The buffer was allocated for t->kcov_size unsigned longs.
+ */
+ area = (u64 *)t->kcov_area;
+ max_pos = t->kcov_size * sizeof(unsigned long);
+
+ count = READ_ONCE(area[0]);
+
+ /* Every record is KCOV_WORDS_PER_CMP 64-bit words. */
+ start_index = 1 + count * KCOV_WORDS_PER_CMP;
+ end_pos = (start_index + KCOV_WORDS_PER_CMP) * sizeof(u64);
+ if (likely(end_pos <= max_pos)) {
+ area[start_index] = type;
+ area[start_index + 1] = arg1;
+ area[start_index + 2] = arg2;
+ area[start_index + 3] = ip;
+ WRITE_ONCE(area[0], count + 1);
+ }
+}
+
+void notrace __sanitizer_cov_trace_cmp1(u8 arg1, u8 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(0), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp1);
+
+void notrace __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(1), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp2);
+
+void notrace __sanitizer_cov_trace_cmp4(u32 arg1, u32 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(2), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp4);
+
+void notrace __sanitizer_cov_trace_cmp8(u64 arg1, u64 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(3), arg1, arg2, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_cmp8);
+
+void notrace __sanitizer_cov_trace_const_cmp1(u8 arg1, u8 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(0) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp1);
+
+void notrace __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(1) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp2);
+
+void notrace __sanitizer_cov_trace_const_cmp4(u32 arg1, u32 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(2) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp4);
+
+void notrace __sanitizer_cov_trace_const_cmp8(u64 arg1, u64 arg2)
+{
+ write_comp_data(KCOV_CMP_SIZE(3) | KCOV_CMP_CONST, arg1, arg2,
+ _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp8);
+
+void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases)
+{
+ u64 i;
+ u64 count = cases[0];
+ u64 size = cases[1];
+ u64 type = KCOV_CMP_CONST;
+
+ switch (size) {
+ case 8:
+ type |= KCOV_CMP_SIZE(0);
+ break;
+ case 16:
+ type |= KCOV_CMP_SIZE(1);
+ break;
+ case 32:
+ type |= KCOV_CMP_SIZE(2);
+ break;
+ case 64:
+ type |= KCOV_CMP_SIZE(3);
+ break;
+ default:
+ return;
+ }
+ for (i = 0; i < count; i++)
+ write_comp_data(type, cases[i + 2], val, _RET_IP_);
+}
+EXPORT_SYMBOL(__sanitizer_cov_trace_switch);
+#endif /* ifdef CONFIG_KCOV_ENABLE_COMPARISONS */
+
+static void kcov_get(struct kcov *kcov)
+{
+ atomic_inc(&kcov->refcount);
+}
+
+static void kcov_put(struct kcov *kcov)
+{
+ if (atomic_dec_and_test(&kcov->refcount)) {
+ vfree(kcov->area);
+ kfree(kcov);
+ }
+}
+
+void kcov_task_init(struct task_struct *t)
+{
+ t->kcov_mode = KCOV_MODE_DISABLED;
+ t->kcov_size = 0;
+ t->kcov_area = NULL;
+ t->kcov = NULL;
+}
+
+void kcov_task_exit(struct task_struct *t)
+{
+ struct kcov *kcov;
+
+ kcov = t->kcov;
+ if (kcov == NULL)
+ return;
+ spin_lock(&kcov->lock);
+ if (WARN_ON(kcov->t != t)) {
+ spin_unlock(&kcov->lock);
+ return;
+ }
+ /* Just to not leave dangling references behind. */
+ kcov_task_init(t);
+ kcov->t = NULL;
+ kcov->mode = KCOV_MODE_INIT;
+ spin_unlock(&kcov->lock);
+ kcov_put(kcov);
+}
+
+static int kcov_mmap(struct file *filep, struct vm_area_struct *vma)
+{
+ int res = 0;
+ void *area;
+ struct kcov *kcov = vma->vm_file->private_data;
+ unsigned long size, off;
+ struct page *page;
+
+ area = vmalloc_user(vma->vm_end - vma->vm_start);
+ if (!area)
+ return -ENOMEM;
+
+ spin_lock(&kcov->lock);
+ size = kcov->size * sizeof(unsigned long);
+ if (kcov->mode != KCOV_MODE_INIT || vma->vm_pgoff != 0 ||
+ vma->vm_end - vma->vm_start != size) {
+ res = -EINVAL;
+ goto exit;
+ }
+ if (!kcov->area) {
+ kcov->area = area;
+ vma->vm_flags |= VM_DONTEXPAND;
+ spin_unlock(&kcov->lock);
+ for (off = 0; off < size; off += PAGE_SIZE) {
+ page = vmalloc_to_page(kcov->area + off);
+ if (vm_insert_page(vma, vma->vm_start + off, page))
+ WARN_ONCE(1, "vm_insert_page() failed");
+ }
+ return 0;
+ }
+exit:
+ spin_unlock(&kcov->lock);
+ vfree(area);
+ return res;
+}
+
+static int kcov_open(struct inode *inode, struct file *filep)
+{
+ struct kcov *kcov;
+
+ kcov = kzalloc(sizeof(*kcov), GFP_KERNEL);
+ if (!kcov)
+ return -ENOMEM;
+ kcov->mode = KCOV_MODE_DISABLED;
+ atomic_set(&kcov->refcount, 1);
+ spin_lock_init(&kcov->lock);
+ filep->private_data = kcov;
+ return nonseekable_open(inode, filep);
+}
+
+static int kcov_close(struct inode *inode, struct file *filep)
+{
+ kcov_put(filep->private_data);
+ return 0;
+}
+
+static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd,
+ unsigned long arg)
+{
+ struct task_struct *t;
+ unsigned long size, unused;
+
+ switch (cmd) {
+ case KCOV_INIT_TRACE:
+ /*
+ * Enable kcov in trace mode and setup buffer size.
+ * Must happen before anything else.
+ */
+ if (kcov->mode != KCOV_MODE_DISABLED)
+ return -EBUSY;
+ /*
+ * Size must be at least 2 to hold current position and one PC.
+ * Later we allocate size * sizeof(unsigned long) memory,
+ * that must not overflow.
+ */
+ size = arg;
+ if (size < 2 || size > INT_MAX / sizeof(unsigned long))
+ return -EINVAL;
+ kcov->size = size;
+ kcov->mode = KCOV_MODE_INIT;
+ return 0;
+ case KCOV_ENABLE:
+ /*
+ * Enable coverage for the current task.
+ * At this point user must have been enabled trace mode,
+ * and mmapped the file. Coverage collection is disabled only
+ * at task exit or voluntary by KCOV_DISABLE. After that it can
+ * be enabled for another task.
+ */
+ if (kcov->mode != KCOV_MODE_INIT || !kcov->area)
+ return -EINVAL;
+ if (kcov->t != NULL)
+ return -EBUSY;
+ if (arg == KCOV_TRACE_PC)
+ kcov->mode = KCOV_MODE_TRACE_PC;
+ else if (arg == KCOV_TRACE_CMP)
+#ifdef CONFIG_KCOV_ENABLE_COMPARISONS
+ kcov->mode = KCOV_MODE_TRACE_CMP;
+#else
+ return -ENOTSUPP;
+#endif
+ else
+ return -EINVAL;
+ t = current;
+ /* Cache in task struct for performance. */
+ t->kcov_size = kcov->size;
+ t->kcov_area = kcov->area;
+ /* See comment in check_kcov_mode(). */
+ barrier();
+ WRITE_ONCE(t->kcov_mode, kcov->mode);
+ t->kcov = kcov;
+ kcov->t = t;
+ /* This is put either in kcov_task_exit() or in KCOV_DISABLE. */
+ kcov_get(kcov);
+ return 0;
+ case KCOV_DISABLE:
+ /* Disable coverage for the current task. */
+ unused = arg;
+ if (unused != 0 || current->kcov != kcov)
+ return -EINVAL;
+ t = current;
+ if (WARN_ON(kcov->t != t))
+ return -EINVAL;
+ kcov_task_init(t);
+ kcov->t = NULL;
+ kcov->mode = KCOV_MODE_INIT;
+ kcov_put(kcov);
+ return 0;
+ default:
+ return -ENOTTY;
+ }
+}
+
+static long kcov_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
+{
+ struct kcov *kcov;
+ int res;
+
+ kcov = filep->private_data;
+ spin_lock(&kcov->lock);
+ res = kcov_ioctl_locked(kcov, cmd, arg);
+ spin_unlock(&kcov->lock);
+ return res;
+}
+
+static const struct file_operations kcov_fops = {
+ .open = kcov_open,
+ .unlocked_ioctl = kcov_ioctl,
+ .compat_ioctl = kcov_ioctl,
+ .mmap = kcov_mmap,
+ .release = kcov_close,
+};
+
+static int __init kcov_init(void)
+{
+ if (!debugfs_create_file("kcov", 0600, NULL, NULL, &kcov_fops)) {
+ pr_err("failed to create kcov in debugfs\n");
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+device_initcall(kcov_init);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index d10ab6b9b5e0..a53998cba804 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -125,7 +125,7 @@ static void *alloc_insn_page(void)
return module_alloc(PAGE_SIZE);
}
-static void free_insn_page(void *page)
+void __weak free_insn_page(void *page)
{
module_memfree(page);
}
@@ -563,7 +563,7 @@ static void kprobe_optimizer(struct work_struct *work)
}
/* Wait for completing optimization and unoptimization */
-static void wait_for_kprobe_optimizer(void)
+void wait_for_kprobe_optimizer(void)
{
mutex_lock(&kprobe_mutex);
@@ -665,7 +665,7 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
}
/* Cancel unoptimizing for reusing */
-static void reuse_unused_kprobe(struct kprobe *ap)
+static int reuse_unused_kprobe(struct kprobe *ap)
{
struct optimized_kprobe *op;
@@ -681,8 +681,11 @@ static void reuse_unused_kprobe(struct kprobe *ap)
/* Enable the probe again */
ap->flags &= ~KPROBE_FLAG_DISABLED;
/* Optimize it again (remove from op->list) */
- BUG_ON(!kprobe_optready(ap));
+ if (!kprobe_optready(ap))
+ return -EINVAL;
+
optimize_kprobe(ap);
+ return 0;
}
/* Remove optimized instructions */
@@ -894,11 +897,16 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt)
#define kprobe_disarmed(p) kprobe_disabled(p)
#define wait_for_kprobe_optimizer() do {} while (0)
-/* There should be no unused kprobes can be reused without optimization */
-static void reuse_unused_kprobe(struct kprobe *ap)
+static int reuse_unused_kprobe(struct kprobe *ap)
{
+ /*
+ * If the optimized kprobe is NOT supported, the aggr kprobe is
+ * released at the same time that the last aggregated kprobe is
+ * unregistered.
+ * Thus there should be no chance to reuse unused kprobe.
+ */
printk(KERN_ERR "Error: There should be no unused kprobe here.\n");
- BUG_ON(kprobe_unused(ap));
+ return -EINVAL;
}
static void free_aggr_kprobe(struct kprobe *p)
@@ -1276,9 +1284,12 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
goto out;
}
init_aggr_kprobe(ap, orig_p);
- } else if (kprobe_unused(ap))
+ } else if (kprobe_unused(ap)) {
/* This probe is going to die. Rescue it */
- reuse_unused_kprobe(ap);
+ ret = reuse_unused_kprobe(ap);
+ if (ret)
+ goto out;
+ }
if (kprobe_gone(ap)) {
/*
@@ -2441,7 +2452,7 @@ static int __init debugfs_kprobe_init(void)
if (!dir)
return -ENOMEM;
- file = debugfs_create_file("list", 0444, dir, NULL,
+ file = debugfs_create_file("list", 0400, dir, NULL,
&debugfs_kprobes_operations);
if (!file)
goto error;
@@ -2451,7 +2462,7 @@ static int __init debugfs_kprobe_init(void)
if (!file)
goto error;
- file = debugfs_create_file("blacklist", 0444, dir, NULL,
+ file = debugfs_create_file("blacklist", 0400, dir, NULL,
&debugfs_kprobe_blacklist_ops);
if (!file)
goto error;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 9ff173dca1ae..f529aafc1180 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -18,6 +18,7 @@
#include <linux/freezer.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
+#include <linux/cgroup.h>
#include <trace/events/sched.h>
static DEFINE_SPINLOCK(kthread_create_lock);
@@ -64,7 +65,7 @@ static inline struct kthread *to_kthread(struct task_struct *k)
static struct kthread *to_live_kthread(struct task_struct *k)
{
struct completion *vfork = ACCESS_ONCE(k->vfork_done);
- if (likely(vfork))
+ if (likely(vfork) && try_get_task_stack(k))
return __to_kthread(vfork);
return NULL;
}
@@ -205,6 +206,7 @@ static int kthread(void *_create)
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
+ cgroup_kthread_ready();
__kthread_parkme(&self);
ret = threadfn(data);
}
@@ -311,10 +313,16 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
task = create->result;
if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
+ char name[TASK_COMM_LEN];
va_list args;
va_start(args, namefmt);
- vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+ /*
+ * task is already visible to other tasks, so updating
+ * COMM must be protected.
+ */
+ vsnprintf(name, sizeof(name), namefmt, args);
+ set_task_comm(task, name);
va_end(args);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
@@ -425,8 +433,10 @@ void kthread_unpark(struct task_struct *k)
{
struct kthread *kthread = to_live_kthread(k);
- if (kthread)
+ if (kthread) {
__kthread_unpark(k, kthread);
+ put_task_stack(k);
+ }
}
EXPORT_SYMBOL_GPL(kthread_unpark);
@@ -455,6 +465,7 @@ int kthread_park(struct task_struct *k)
wait_for_completion(&kthread->parked);
}
}
+ put_task_stack(k);
ret = 0;
}
return ret;
@@ -490,6 +501,7 @@ int kthread_stop(struct task_struct *k)
__kthread_unpark(k, kthread);
wake_up_process(k);
wait_for_completion(&kthread->exited);
+ put_task_stack(k);
}
ret = k->exit_code;
put_task_struct(k);
@@ -510,6 +522,7 @@ int kthreadd(void *unused)
set_mems_allowed(node_states[N_MEMORY]);
current->flags |= PF_NOFREEZE;
+ cgroup_init_kthreadd();
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
@@ -601,6 +614,19 @@ repeat:
}
EXPORT_SYMBOL_GPL(kthread_worker_fn);
+/*
+ * Returns true when the work could not be queued at the moment.
+ * It happens when it is already pending in a worker list
+ * or when it is being cancelled.
+ */
+static inline bool queuing_blocked(struct kthread_worker *worker,
+ struct kthread_work *work)
+{
+ lockdep_assert_held(&worker->lock);
+
+ return !list_empty(&work->node) || work->canceling;
+}
+
/* insert @work before @pos in @worker */
static void insert_kthread_work(struct kthread_worker *worker,
struct kthread_work *work,
@@ -630,7 +656,7 @@ bool queue_kthread_work(struct kthread_worker *worker,
unsigned long flags;
spin_lock_irqsave(&worker->lock, flags);
- if (list_empty(&work->node)) {
+ if (!queuing_blocked(worker, work)) {
insert_kthread_work(worker, work, &worker->work_list);
ret = true;
}
@@ -691,6 +717,87 @@ retry:
}
EXPORT_SYMBOL_GPL(flush_kthread_work);
+/*
+ * This function removes the work from the worker queue. Also it makes sure
+ * that it won't get queued later via the delayed work's timer.
+ *
+ * The work might still be in use when this function finishes. See the
+ * current_work proceed by the worker.
+ *
+ * Return: %true if @work was pending and successfully canceled,
+ * %false if @work was not pending
+ */
+static bool __kthread_cancel_work(struct kthread_work *work,
+ unsigned long *flags)
+{
+ /*
+ * Try to remove the work from a worker list. It might either
+ * be from worker->work_list or from worker->delayed_work_list.
+ */
+ if (!list_empty(&work->node)) {
+ list_del_init(&work->node);
+ return true;
+ }
+
+ return false;
+}
+
+static bool __kthread_cancel_work_sync(struct kthread_work *work)
+{
+ struct kthread_worker *worker = work->worker;
+ unsigned long flags;
+ int ret = false;
+
+ if (!worker)
+ goto out;
+
+ spin_lock_irqsave(&worker->lock, flags);
+ /* Work must not be used with >1 worker, see kthread_queue_work(). */
+ WARN_ON_ONCE(work->worker != worker);
+
+ ret = __kthread_cancel_work(work, &flags);
+
+ if (worker->current_work != work)
+ goto out_fast;
+
+ /*
+ * The work is in progress and we need to wait with the lock released.
+ * In the meantime, block any queuing by setting the canceling counter.
+ */
+ work->canceling++;
+ spin_unlock_irqrestore(&worker->lock, flags);
+ flush_kthread_work(work);
+ spin_lock_irqsave(&worker->lock, flags);
+ work->canceling--;
+
+out_fast:
+ spin_unlock_irqrestore(&worker->lock, flags);
+out:
+ return ret;
+}
+
+/**
+ * kthread_cancel_work_sync - cancel a kthread work and wait for it to finish
+ * @work: the kthread work to cancel
+ *
+ * Cancel @work and wait for its execution to finish. This function
+ * can be used even if the work re-queues itself. On return from this
+ * function, @work is guaranteed to be not pending or executing on any CPU.
+ *
+ * kthread_cancel_work_sync(&delayed_work->work) must not be used for
+ * delayed_work's. Use kthread_cancel_delayed_work_sync() instead.
+ *
+ * The caller must ensure that the worker on which @work was last
+ * queued can't be destroyed before this function returns.
+ *
+ * Return: %true if @work was pending, %false otherwise.
+ */
+bool kthread_cancel_work_sync(struct kthread_work *work)
+{
+ return __kthread_cancel_work_sync(work);
+}
+EXPORT_SYMBOL_GPL(kthread_cancel_work_sync);
+
/**
* flush_kthread_worker - flush all current works on a kthread_worker
* @worker: worker to flush
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 8e96f6cc2a4a..31322a4275cd 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,3 +1,6 @@
+# Any varying coverage in these files is non-deterministic
+# and is generally not a function of system call inputs.
+KCOV_INSTRUMENT := n
obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 60ace56618f6..774ab79d3ec7 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1264,11 +1264,11 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_forward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
@@ -1291,11 +1291,11 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_backward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
@@ -3128,10 +3128,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
if (depth) {
hlock = curr->held_locks + depth - 1;
if (hlock->class_idx == class_idx && nest_lock) {
- if (hlock->references)
+ if (hlock->references) {
+ /*
+ * Check: unsigned int references:12, overflow.
+ */
+ if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
+ return 0;
+
hlock->references++;
- else
+ } else {
hlock->references = 2;
+ }
return 1;
}
@@ -3819,7 +3826,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
- if (unlikely(!lock_stat))
+ if (unlikely(!lock_stat || !debug_locks))
return;
if (unlikely(current->lockdep_recursion))
@@ -3839,7 +3846,7 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
- if (unlikely(!lock_stat))
+ if (unlikely(!lock_stat || !debug_locks))
return;
if (unlikely(current->lockdep_recursion))
@@ -4116,7 +4123,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
if (unlikely(!debug_locks))
return;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
for (i = 0; i < curr->lockdep_depth; i++) {
hlock = curr->held_locks + i;
@@ -4127,7 +4134,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock);
break;
}
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8ef1919d63b2..d580b7d6ee6d 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -776,6 +776,8 @@ static void lock_torture_cleanup(void)
else
lock_torture_print_module_parms(cxt.cur_ops,
"End of test: SUCCESS");
+ kfree(cxt.lwsa);
+ kfree(cxt.lrsa);
torture_cleanup_end();
}
@@ -917,6 +919,8 @@ static int __init lock_torture_init(void)
GFP_KERNEL);
if (reader_tasks == NULL) {
VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+ kfree(writer_tasks);
+ writer_tasks = NULL;
firsterr = -ENOMEM;
goto unwind;
}
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 3ef3736002d8..9c951fade415 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -49,21 +49,21 @@ void debug_mutex_free_waiter(struct mutex_waiter *waiter)
}
void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti)
+ struct task_struct *task)
{
SMP_DEBUG_LOCKS_WARN_ON(!spin_is_locked(&lock->wait_lock));
/* Mark the current thread as blocked on the lock: */
- ti->task->blocked_on = waiter;
+ task->blocked_on = waiter;
}
void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti)
+ struct task_struct *task)
{
DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
- DEBUG_LOCKS_WARN_ON(waiter->task != ti->task);
- DEBUG_LOCKS_WARN_ON(ti->task->blocked_on != waiter);
- ti->task->blocked_on = NULL;
+ DEBUG_LOCKS_WARN_ON(waiter->task != task);
+ DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
+ task->blocked_on = NULL;
list_del_init(&waiter->list);
waiter->task = NULL;
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 0799fd3e4cfa..d06ae3bb46c5 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -20,9 +20,9 @@ extern void debug_mutex_wake_waiter(struct mutex *lock,
extern void debug_mutex_free_waiter(struct mutex_waiter *waiter);
extern void debug_mutex_add_waiter(struct mutex *lock,
struct mutex_waiter *waiter,
- struct thread_info *ti);
+ struct task_struct *task);
extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
- struct thread_info *ti);
+ struct task_struct *task);
extern void debug_mutex_unlock(struct mutex *lock);
extern void debug_mutex_init(struct mutex *lock, const char *name,
struct lock_class_key *key);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 89350f924c85..a70b90db3909 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -537,7 +537,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
goto skip_wait;
debug_mutex_lock_common(lock, &waiter);
- debug_mutex_add_waiter(lock, &waiter, task_thread_info(task));
+ debug_mutex_add_waiter(lock, &waiter, task);
/* add waiting tasks to the end of the waitqueue (FIFO): */
list_add_tail(&waiter.list, &lock->wait_list);
@@ -584,7 +584,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
}
__set_task_state(task, TASK_RUNNING);
- mutex_remove_waiter(lock, &waiter, current_thread_info());
+ mutex_remove_waiter(lock, &waiter, task);
/* set it to 0 if there are no waiters left: */
if (likely(list_empty(&lock->wait_list)))
atomic_set(&lock->count, 0);
@@ -605,7 +605,7 @@ skip_wait:
return 0;
err:
- mutex_remove_waiter(lock, &waiter, task_thread_info(task));
+ mutex_remove_waiter(lock, &waiter, task);
spin_unlock_mutex(&lock->wait_lock, flags);
debug_mutex_free_waiter(&waiter);
mutex_release(&lock->dep_map, 1, ip);
@@ -719,6 +719,7 @@ static inline void
__mutex_unlock_common_slowpath(struct mutex *lock, int nested)
{
unsigned long flags;
+ WAKE_Q(wake_q);
/*
* As a performance measurement, release the lock before doing other
@@ -746,11 +747,11 @@ __mutex_unlock_common_slowpath(struct mutex *lock, int nested)
struct mutex_waiter, list);
debug_mutex_wake_waiter(lock, waiter);
-
- wake_up_process(waiter->task);
+ wake_q_add(&wake_q, waiter->task);
}
spin_unlock_mutex(&lock->wait_lock, flags);
+ wake_up_q(&wake_q);
}
/*
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 5cda397607f2..a68bae5e852a 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -13,7 +13,7 @@
do { spin_lock(lock); (void)(flags); } while (0)
#define spin_unlock_mutex(lock, flags) \
do { spin_unlock(lock); (void)(flags); } while (0)
-#define mutex_remove_waiter(lock, waiter, ti) \
+#define mutex_remove_waiter(lock, waiter, task) \
__list_del((waiter)->list.prev, (waiter)->list.next)
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 05a37857ab55..8d7047ecef4e 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -104,6 +104,19 @@ bool osq_lock(struct optimistic_spin_queue *lock)
prev = decode_cpu(old);
node->prev = prev;
+
+ /*
+ * osq_lock() unqueue
+ *
+ * node->prev = prev osq_wait_next()
+ * WMB MB
+ * prev->next = node next->prev = prev // unqueue-C
+ *
+ * Here 'node->prev' and 'next->prev' are the same variable and we need
+ * to ensure these stores happen in-order to avoid corrupting the list.
+ */
+ smp_wmb();
+
WRITE_ONCE(prev->next, node);
/*
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index f231e0bb311c..ce182599cf2e 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -8,151 +8,186 @@
#include <linux/sched.h>
#include <linux/errno.h>
-int __percpu_init_rwsem(struct percpu_rw_semaphore *brw,
+int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
const char *name, struct lock_class_key *rwsem_key)
{
- brw->fast_read_ctr = alloc_percpu(int);
- if (unlikely(!brw->fast_read_ctr))
+ sem->read_count = alloc_percpu(int);
+ if (unlikely(!sem->read_count))
return -ENOMEM;
/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
- __init_rwsem(&brw->rw_sem, name, rwsem_key);
- rcu_sync_init(&brw->rss, RCU_SCHED_SYNC);
- atomic_set(&brw->slow_read_ctr, 0);
- init_waitqueue_head(&brw->write_waitq);
+ rcu_sync_init(&sem->rss, RCU_SCHED_SYNC);
+ __init_rwsem(&sem->rw_sem, name, rwsem_key);
+ init_waitqueue_head(&sem->writer);
+ sem->readers_block = 0;
return 0;
}
EXPORT_SYMBOL_GPL(__percpu_init_rwsem);
-void percpu_free_rwsem(struct percpu_rw_semaphore *brw)
+void percpu_free_rwsem(struct percpu_rw_semaphore *sem)
{
/*
* XXX: temporary kludge. The error path in alloc_super()
* assumes that percpu_free_rwsem() is safe after kzalloc().
*/
- if (!brw->fast_read_ctr)
+ if (!sem->read_count)
return;
- rcu_sync_dtor(&brw->rss);
- free_percpu(brw->fast_read_ctr);
- brw->fast_read_ctr = NULL; /* catch use after free bugs */
+ rcu_sync_dtor(&sem->rss);
+ free_percpu(sem->read_count);
+ sem->read_count = NULL; /* catch use after free bugs */
}
+EXPORT_SYMBOL_GPL(percpu_free_rwsem);
-/*
- * This is the fast-path for down_read/up_read. If it succeeds we rely
- * on the barriers provided by rcu_sync_enter/exit; see the comments in
- * percpu_down_write() and percpu_up_write().
- *
- * If this helper fails the callers rely on the normal rw_semaphore and
- * atomic_dec_and_test(), so in this case we have the necessary barriers.
- */
-static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val)
+int __percpu_down_read(struct percpu_rw_semaphore *sem, int try)
{
- bool success;
+ /*
+ * Due to having preemption disabled the decrement happens on
+ * the same CPU as the increment, avoiding the
+ * increment-on-one-CPU-and-decrement-on-another problem.
+ *
+ * If the reader misses the writer's assignment of readers_block, then
+ * the writer is guaranteed to see the reader's increment.
+ *
+ * Conversely, any readers that increment their sem->read_count after
+ * the writer looks are guaranteed to see the readers_block value,
+ * which in turn means that they are guaranteed to immediately
+ * decrement their sem->read_count, so that it doesn't matter that the
+ * writer missed them.
+ */
- preempt_disable();
- success = rcu_sync_is_idle(&brw->rss);
- if (likely(success))
- __this_cpu_add(*brw->fast_read_ctr, val);
- preempt_enable();
+ smp_mb(); /* A matches D */
- return success;
-}
+ /*
+ * If !readers_block the critical section starts here, matched by the
+ * release in percpu_up_write().
+ */
+ if (likely(!smp_load_acquire(&sem->readers_block)))
+ return 1;
-/*
- * Like the normal down_read() this is not recursive, the writer can
- * come after the first percpu_down_read() and create the deadlock.
- *
- * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep,
- * percpu_up_read() does rwsem_release(). This pairs with the usage
- * of ->rw_sem in percpu_down/up_write().
- */
-void percpu_down_read(struct percpu_rw_semaphore *brw)
-{
- might_sleep();
- rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_);
+ /*
+ * Per the above comment; we still have preemption disabled and
+ * will thus decrement on the same CPU as we incremented.
+ */
+ __percpu_up_read(sem);
- if (likely(update_fast_ctr(brw, +1)))
- return;
+ if (try)
+ return 0;
- /* Avoid rwsem_acquire_read() and rwsem_release() */
- __down_read(&brw->rw_sem);
- atomic_inc(&brw->slow_read_ctr);
- __up_read(&brw->rw_sem);
-}
-EXPORT_SYMBOL_GPL(percpu_down_read);
+ /*
+ * We either call schedule() in the wait, or we'll fall through
+ * and reschedule on the preempt_enable() in percpu_down_read().
+ */
+ preempt_enable_no_resched();
-int percpu_down_read_trylock(struct percpu_rw_semaphore *brw)
-{
- if (unlikely(!update_fast_ctr(brw, +1))) {
- if (!__down_read_trylock(&brw->rw_sem))
- return 0;
- atomic_inc(&brw->slow_read_ctr);
- __up_read(&brw->rw_sem);
- }
-
- rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 1, _RET_IP_);
+ /*
+ * Avoid lockdep for the down/up_read() we already have them.
+ */
+ __down_read(&sem->rw_sem);
+ this_cpu_inc(*sem->read_count);
+ __up_read(&sem->rw_sem);
+
+ preempt_disable();
return 1;
}
+EXPORT_SYMBOL_GPL(__percpu_down_read);
-void percpu_up_read(struct percpu_rw_semaphore *brw)
+void __percpu_up_read(struct percpu_rw_semaphore *sem)
{
- rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_);
-
- if (likely(update_fast_ctr(brw, -1)))
- return;
+ smp_mb(); /* B matches C */
+ /*
+ * In other words, if they see our decrement (presumably to aggregate
+ * zero, as that is the only time it matters) they will also see our
+ * critical section.
+ */
+ __this_cpu_dec(*sem->read_count);
- /* false-positive is possible but harmless */
- if (atomic_dec_and_test(&brw->slow_read_ctr))
- wake_up_all(&brw->write_waitq);
+ /* Prod writer to recheck readers_active */
+ wake_up(&sem->writer);
}
-EXPORT_SYMBOL_GPL(percpu_up_read);
+EXPORT_SYMBOL_GPL(__percpu_up_read);
+
+#define per_cpu_sum(var) \
+({ \
+ typeof(var) __sum = 0; \
+ int cpu; \
+ compiletime_assert_atomic_type(__sum); \
+ for_each_possible_cpu(cpu) \
+ __sum += per_cpu(var, cpu); \
+ __sum; \
+})
-static int clear_fast_ctr(struct percpu_rw_semaphore *brw)
+/*
+ * Return true if the modular sum of the sem->read_count per-CPU variable is
+ * zero. If this sum is zero, then it is stable due to the fact that if any
+ * newly arriving readers increment a given counter, they will immediately
+ * decrement that same counter.
+ */
+static bool readers_active_check(struct percpu_rw_semaphore *sem)
{
- unsigned int sum = 0;
- int cpu;
+ if (per_cpu_sum(*sem->read_count) != 0)
+ return false;
+
+ /*
+ * If we observed the decrement; ensure we see the entire critical
+ * section.
+ */
- for_each_possible_cpu(cpu) {
- sum += per_cpu(*brw->fast_read_ctr, cpu);
- per_cpu(*brw->fast_read_ctr, cpu) = 0;
- }
+ smp_mb(); /* C matches B */
- return sum;
+ return true;
}
-void percpu_down_write(struct percpu_rw_semaphore *brw)
+void percpu_down_write(struct percpu_rw_semaphore *sem)
{
+ /* Notify readers to take the slow path. */
+ rcu_sync_enter(&sem->rss);
+
+ down_write(&sem->rw_sem);
+
/*
- * Make rcu_sync_is_idle() == F and thus disable the fast-path in
- * percpu_down_read() and percpu_up_read(), and wait for gp pass.
- *
- * The latter synchronises us with the preceding readers which used
- * the fast-past, so we can not miss the result of __this_cpu_add()
- * or anything else inside their criticial sections.
+ * Notify new readers to block; up until now, and thus throughout the
+ * longish rcu_sync_enter() above, new readers could still come in.
*/
- rcu_sync_enter(&brw->rss);
+ WRITE_ONCE(sem->readers_block, 1);
- /* exclude other writers, and block the new readers completely */
- down_write(&brw->rw_sem);
+ smp_mb(); /* D matches A */
- /* nobody can use fast_read_ctr, move its sum into slow_read_ctr */
- atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr);
+ /*
+ * If they don't see our writer of readers_block, then we are
+ * guaranteed to see their sem->read_count increment, and therefore
+ * will wait for them.
+ */
- /* wait for all readers to complete their percpu_up_read() */
- wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr));
+ /* Wait for all now active readers to complete. */
+ wait_event(sem->writer, readers_active_check(sem));
}
EXPORT_SYMBOL_GPL(percpu_down_write);
-void percpu_up_write(struct percpu_rw_semaphore *brw)
+void percpu_up_write(struct percpu_rw_semaphore *sem)
{
- /* release the lock, but the readers can't use the fast-path */
- up_write(&brw->rw_sem);
/*
- * Enable the fast-path in percpu_down_read() and percpu_up_read()
- * but only after another gp pass; this adds the necessary barrier
- * to ensure the reader can't miss the changes done by us.
+ * Signal the writer is done, no fast path yet.
+ *
+ * One reason that we cannot just immediately flip to readers_fast is
+ * that new readers might fail to see the results of this writer's
+ * critical section.
+ *
+ * Therefore we force it through the slow path which guarantees an
+ * acquire and thereby guarantees the critical section's consistency.
+ */
+ smp_store_release(&sem->readers_block, 0);
+
+ /*
+ * Release the write lock, this will allow readers back in the game.
+ */
+ up_write(&sem->rw_sem);
+
+ /*
+ * Once this completes (at least one RCU-sched grace period hence) the
+ * reader fast path will be available again. Safe to use outside the
+ * exclusive write lock because its counting.
*/
- rcu_sync_exit(&brw->rss);
+ rcu_sync_exit(&sem->rss);
}
EXPORT_SYMBOL_GPL(percpu_up_write);
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 8173bc7fec92..3b40c8809e52 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -423,6 +423,14 @@ queue:
tail = encode_tail(smp_processor_id(), idx);
node += idx;
+
+ /*
+ * Ensure that we increment the head node->count before initialising
+ * the actual node. If the compiler is kind enough to reorder these
+ * stores, then an IRQ could overwrite our assignments.
+ */
+ barrier();
+
node->locked = 0;
node->next = NULL;
pv_init_node(node);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 8251e75dd9c0..dd173df9ee5e 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -65,8 +65,72 @@ static inline void clear_rt_mutex_waiters(struct rt_mutex *lock)
static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
{
- if (!rt_mutex_has_waiters(lock))
- clear_rt_mutex_waiters(lock);
+ unsigned long owner, *p = (unsigned long *) &lock->owner;
+
+ if (rt_mutex_has_waiters(lock))
+ return;
+
+ /*
+ * The rbtree has no waiters enqueued, now make sure that the
+ * lock->owner still has the waiters bit set, otherwise the
+ * following can happen:
+ *
+ * CPU 0 CPU 1 CPU2
+ * l->owner=T1
+ * rt_mutex_lock(l)
+ * lock(l->lock)
+ * l->owner = T1 | HAS_WAITERS;
+ * enqueue(T2)
+ * boost()
+ * unlock(l->lock)
+ * block()
+ *
+ * rt_mutex_lock(l)
+ * lock(l->lock)
+ * l->owner = T1 | HAS_WAITERS;
+ * enqueue(T3)
+ * boost()
+ * unlock(l->lock)
+ * block()
+ * signal(->T2) signal(->T3)
+ * lock(l->lock)
+ * dequeue(T2)
+ * deboost()
+ * unlock(l->lock)
+ * lock(l->lock)
+ * dequeue(T3)
+ * ==> wait list is empty
+ * deboost()
+ * unlock(l->lock)
+ * lock(l->lock)
+ * fixup_rt_mutex_waiters()
+ * if (wait_list_empty(l) {
+ * l->owner = owner
+ * owner = l->owner & ~HAS_WAITERS;
+ * ==> l->owner = T1
+ * }
+ * lock(l->lock)
+ * rt_mutex_unlock(l) fixup_rt_mutex_waiters()
+ * if (wait_list_empty(l) {
+ * owner = l->owner & ~HAS_WAITERS;
+ * cmpxchg(l->owner, T1, NULL)
+ * ===> Success (l->owner = NULL)
+ *
+ * l->owner = owner
+ * ==> l->owner = T1
+ * }
+ *
+ * With the check for the waiter bit in place T3 on CPU2 will not
+ * overwrite. All tasks fiddling with the waiters bit are
+ * serialized by l->lock, so nothing else can modify the waiters
+ * bit. If the bit is set then nothing can change l->owner either
+ * so the simple RMW is safe. The cmpxchg() will simply fail if it
+ * happens in the middle of the RMW because the waiters bit is
+ * still set.
+ */
+ owner = READ_ONCE(*p);
+ if (owner & RT_MUTEX_HAS_WAITERS)
+ WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
}
/*
@@ -1648,21 +1712,23 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
}
/**
- * rt_mutex_finish_proxy_lock() - Complete lock acquisition
+ * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
* @lock: the rt_mutex we were woken on
* @to: the timeout, null if none. hrtimer should already have
* been started.
* @waiter: the pre-initialized rt_mutex_waiter
*
- * Complete the lock acquisition started our behalf by another thread.
+ * Wait for the the lock acquisition started on our behalf by
+ * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
+ * rt_mutex_cleanup_proxy_lock().
*
* Returns:
* 0 - success
* <0 - error, one of -EINTR, -ETIMEDOUT
*
- * Special API call for PI-futex requeue support
+ * Special API call for PI-futex support
*/
-int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *to,
struct rt_mutex_waiter *waiter)
{
@@ -1675,9 +1741,6 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
/* sleep on the mutex */
ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
- if (unlikely(ret))
- remove_waiter(lock, waiter);
-
/*
* try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
* have to fix that up.
@@ -1688,3 +1751,42 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
return ret;
}
+
+/**
+ * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
+ * @lock: the rt_mutex we were woken on
+ * @waiter: the pre-initialized rt_mutex_waiter
+ *
+ * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ *
+ * Unless we acquired the lock; we're still enqueued on the wait-list and can
+ * in fact still be granted ownership until we're removed. Therefore we can
+ * find we are in fact the owner and must disregard the
+ * rt_mutex_wait_proxy_lock() failure.
+ *
+ * Returns:
+ * true - did the cleanup, we done.
+ * false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
+ * caller should disregards its return value.
+ *
+ * Special API call for PI-futex support
+ */
+bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter)
+{
+ bool cleanup = false;
+
+ raw_spin_lock_irq(&lock->wait_lock);
+ /*
+ * Unless we're the owner; we're still enqueued on the wait_list.
+ * So check if we became owner, if not, take us off the wait_list.
+ */
+ if (rt_mutex_owner(lock) != current) {
+ remove_waiter(lock, waiter);
+ fixup_rt_mutex_waiters(lock);
+ cleanup = true;
+ }
+ raw_spin_unlock_irq(&lock->wait_lock);
+
+ return cleanup;
+}
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 4f5f83c7d2d3..6f8f68edb700 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -75,8 +75,9 @@ task_top_pi_waiter(struct task_struct *p)
static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
{
- return (struct task_struct *)
- ((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
+ unsigned long owner = (unsigned long) READ_ONCE(lock->owner);
+
+ return (struct task_struct *) (owner & ~RT_MUTEX_OWNER_MASKALL);
}
/*
@@ -105,9 +106,11 @@ extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
struct task_struct *task);
-extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
- struct hrtimer_sleeper *to,
- struct rt_mutex_waiter *waiter);
+extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
+ struct hrtimer_sleeper *to,
+ struct rt_mutex_waiter *waiter);
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter);
extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
extern bool rt_mutex_futex_unlock(struct rt_mutex *lock,
struct wake_q_head *wqh);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index a4d4de05b2d1..1be33caf157d 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -511,6 +511,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
unsigned long flags;
/*
+ * __rwsem_down_write_failed_common(sem)
+ * rwsem_optimistic_spin(sem)
+ * osq_unlock(sem->osq)
+ * ...
+ * atomic_long_add_return(&sem->count)
+ *
+ * - VS -
+ *
+ * __up_write()
+ * if (atomic_long_sub_return_release(&sem->count) < 0)
+ * rwsem_wake(sem)
+ * osq_is_locked(&sem->osq)
+ *
+ * And __up_write() must observe !osq_is_locked() when it observes the
+ * atomic_long_add_return() in order to not miss a wakeup.
+ *
+ * This boils down to:
+ *
+ * [S.rel] X = 1 [RmW] r0 = (Y += 0)
+ * MB RMB
+ * [RmW] Y += 1 [L] r1 = X
+ *
+ * exists (r0=1 /\ r1=0)
+ */
+ smp_rmb();
+
+ /*
* If a spinner is present, it is not necessary to do the wakeup.
* Try to do wakeup only if the trylock succeeds to minimize
* spinlock contention which may introduce too much delay in the
diff --git a/kernel/membarrier.c b/kernel/membarrier.c
index 536c727a56e9..9f9284f37f8d 100644
--- a/kernel/membarrier.c
+++ b/kernel/membarrier.c
@@ -16,6 +16,7 @@
#include <linux/syscalls.h>
#include <linux/membarrier.h>
+#include <linux/tick.h>
/*
* Bitmask made from a "or" of all commands within enum membarrier_cmd,
@@ -51,6 +52,9 @@
*/
SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
{
+ /* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
+ if (tick_nohz_full_enabled())
+ return -ENOSYS;
if (unlikely(flags))
return -EINVAL;
switch (cmd) {
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 25ced161ebeb..1be42f9b3e00 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -159,7 +159,9 @@ static void devm_memremap_pages_release(struct device *dev, void *res)
struct page_map *page_map = res;
/* pages are dead and unused, undo the arch mapping */
+ mem_hotplug_begin();
arch_remove_memory(page_map->res.start, resource_size(&page_map->res));
+ mem_hotplug_done();
}
void *devm_memremap_pages(struct device *dev, struct resource *res)
@@ -169,15 +171,12 @@ void *devm_memremap_pages(struct device *dev, struct resource *res)
struct page_map *page_map;
int error, nid;
- if (is_ram == REGION_MIXED) {
- WARN_ONCE(1, "%s attempted on mixed region %pr\n",
- __func__, res);
+ if (is_ram != REGION_DISJOINT) {
+ WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
+ is_ram == REGION_MIXED ? "mixed" : "ram", res);
return ERR_PTR(-ENXIO);
}
- if (is_ram == REGION_INTERSECTS)
- return __va(res->start);
-
page_map = devres_alloc_node(devm_memremap_pages_release,
sizeof(*page_map), GFP_KERNEL, dev_to_node(dev));
if (!page_map)
@@ -189,7 +188,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res)
if (nid < 0)
nid = numa_mem_id();
+ mem_hotplug_begin();
error = arch_add_memory(nid, res->start, resource_size(res), true);
+ mem_hotplug_done();
if (error) {
devres_free(page_map);
return ERR_PTR(error);
@@ -198,5 +199,5 @@ void *devm_memremap_pages(struct device *dev, struct resource *res)
devres_add(dev, page_map);
return __va(res->start);
}
-EXPORT_SYMBOL(devm_memremap_pages);
+EXPORT_SYMBOL_GPL(devm_memremap_pages);
#endif /* CONFIG_ZONE_DEVICE */
diff --git a/kernel/module.c b/kernel/module.c
index b14a4f31221f..bcc78f4c15e9 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2404,7 +2404,7 @@ static char elf_type(const Elf_Sym *sym, const struct load_info *info)
}
if (sym->st_shndx == SHN_UNDEF)
return 'U';
- if (sym->st_shndx == SHN_ABS)
+ if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu)
return 'a';
if (sym->st_shndx >= SHN_LORESERVE)
return '?';
@@ -2433,7 +2433,7 @@ static char elf_type(const Elf_Sym *sym, const struct load_info *info)
}
static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
- unsigned int shnum)
+ unsigned int shnum, unsigned int pcpundx)
{
const Elf_Shdr *sec;
@@ -2442,6 +2442,11 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
|| !src->st_name)
return false;
+#ifdef CONFIG_KALLSYMS_ALL
+ if (src->st_shndx == pcpundx)
+ return true;
+#endif
+
sec = sechdrs + src->st_shndx;
if (!(sec->sh_flags & SHF_ALLOC)
#ifndef CONFIG_KALLSYMS_ALL
@@ -2479,7 +2484,8 @@ static void layout_symtab(struct module *mod, struct load_info *info)
/* Compute total space required for the core symbols' strtab. */
for (ndst = i = 0; i < nsrc; i++) {
if (i == 0 ||
- is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) {
+ is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum,
+ info->index.pcpu)) {
strtab_size += strlen(&info->strtab[src[i].st_name])+1;
ndst++;
}
@@ -2537,7 +2543,8 @@ static void add_kallsyms(struct module *mod, const struct load_info *info)
src = mod->kallsyms->symtab;
for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) {
if (i == 0 ||
- is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) {
+ is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum,
+ info->index.pcpu)) {
dst[ndst] = src[i];
dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name],
@@ -2862,6 +2869,15 @@ static struct module *setup_load_info(struct load_info *info, int flags)
return mod;
}
+static void check_modinfo_retpoline(struct module *mod, struct load_info *info)
+{
+ if (retpoline_module_ok(get_modinfo(info, "retpoline")))
+ return;
+
+ pr_warn("%s: loading module not compiled with retpoline compiler.\n",
+ mod->name);
+}
+
static int check_modinfo(struct module *mod, struct load_info *info, int flags)
{
const char *modmagic = get_modinfo(info, "vermagic");
@@ -2881,8 +2897,14 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
return -ENOEXEC;
}
- if (!get_modinfo(info, "intree"))
+ if (!get_modinfo(info, "intree")) {
+ if (!test_taint(TAINT_OOT_MODULE))
+ pr_warn("%s: loading out-of-tree module taints kernel.\n",
+ mod->name);
add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK);
+ }
+
+ check_modinfo_retpoline(mod, info);
if (get_modinfo(info, "staging")) {
add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK);
@@ -3047,6 +3069,8 @@ static int move_module(struct module *mod, struct load_info *info)
static int check_module_license_and_versions(struct module *mod)
{
+ int prev_taint = test_taint(TAINT_PROPRIETARY_MODULE);
+
/*
* ndiswrapper is under GPL by itself, but loads proprietary modules.
* Don't use add_taint_module(), as it would prevent ndiswrapper from
@@ -3065,6 +3089,9 @@ static int check_module_license_and_versions(struct module *mod)
add_taint_module(mod, TAINT_PROPRIETARY_MODULE,
LOCKDEP_NOW_UNRELIABLE);
+ if (!prev_taint && test_taint(TAINT_PROPRIETARY_MODULE))
+ pr_warn("%s: module license taints kernel.\n", mod->name);
+
#ifdef CONFIG_MODVERSIONS
if ((mod->num_syms && !mod->crcs)
|| (mod->num_gpl_syms && !mod->gpl_crcs)
@@ -3833,7 +3860,7 @@ static unsigned long mod_find_symname(struct module *mod, const char *name)
for (i = 0; i < kallsyms->num_symtab; i++)
if (strcmp(name, symname(kallsyms, i)) == 0 &&
- kallsyms->symtab[i].st_info != 'U')
+ kallsyms->symtab[i].st_shndx != SHN_UNDEF)
return kallsyms->symtab[i].st_value;
return 0;
}
@@ -3879,6 +3906,10 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
if (mod->state == MODULE_STATE_UNFORMED)
continue;
for (i = 0; i < kallsyms->num_symtab; i++) {
+
+ if (kallsyms->symtab[i].st_shndx == SHN_UNDEF)
+ continue;
+
ret = fn(data, symname(kallsyms, i),
mod, kallsyms->symtab[i].st_value);
if (ret != 0)
diff --git a/kernel/padata.c b/kernel/padata.c
index b38bea9c466a..ecc7b3f452c7 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -189,19 +189,20 @@ static struct padata_priv *padata_get_next(struct parallel_data *pd)
reorder = &next_queue->reorder;
+ spin_lock(&reorder->lock);
if (!list_empty(&reorder->list)) {
padata = list_entry(reorder->list.next,
struct padata_priv, list);
- spin_lock(&reorder->lock);
list_del_init(&padata->list);
atomic_dec(&pd->reorder_objects);
- spin_unlock(&reorder->lock);
pd->processed++;
+ spin_unlock(&reorder->lock);
goto out;
}
+ spin_unlock(&reorder->lock);
if (__this_cpu_read(pd->pqueue->cpu_index) == next_queue->cpu_index) {
padata = ERR_PTR(-ENODATA);
@@ -356,7 +357,7 @@ static int padata_setup_cpumasks(struct parallel_data *pd,
cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask);
if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) {
- free_cpumask_var(pd->cpumask.cbcpu);
+ free_cpumask_var(pd->cpumask.pcpu);
return -ENOMEM;
}
diff --git a/kernel/panic.c b/kernel/panic.c
index 41e2b54f36b5..1d07cf9af849 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -167,7 +167,7 @@ void panic(const char *fmt, ...)
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked.
*/
- pr_emerg("Rebooting in %d seconds..", panic_timeout);
+ pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
touch_nmi_watchdog();
diff --git a/kernel/pid.c b/kernel/pid.c
index 78b3d9f80d44..5fe7cdb6d05f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -322,8 +322,10 @@ struct pid *alloc_pid(struct pid_namespace *ns)
}
if (unlikely(is_child_reaper(pid))) {
- if (pid_ns_prepare_proc(ns))
+ if (pid_ns_prepare_proc(ns)) {
+ disable_pid_allocation(ns);
goto out_free;
+ }
}
get_pid_ns(ns);
@@ -526,8 +528,11 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
if (!ns)
ns = task_active_pid_ns(current);
if (likely(pid_alive(task))) {
- if (type != PIDTYPE_PID)
+ if (type != PIDTYPE_PID) {
+ if (type == __PIDTYPE_TGID)
+ type = PIDTYPE_PID;
task = task->group_leader;
+ }
nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
}
rcu_read_unlock();
@@ -536,12 +541,6 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
}
EXPORT_SYMBOL(__task_pid_nr_ns);
-pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
- return pid_nr_ns(task_tgid(tsk), ns);
-}
-EXPORT_SYMBOL(task_tgid_nr_ns);
-
struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
{
return ns_of_pid(task_pid(tsk));
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index a65ba137fd15..567ecc826bc8 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -255,7 +255,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
* if reparented.
*/
for (;;) {
- set_current_state(TASK_UNINTERRUPTIBLE);
+ set_current_state(TASK_INTERRUPTIBLE);
if (pid_ns->nr_hashed == init_pids)
break;
schedule();
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 02e8dfaa1ce2..4335e7d1c391 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -1,6 +1,7 @@
config SUSPEND
bool "Suspend to RAM and standby"
depends on ARCH_SUSPEND_POSSIBLE
+ select RTC_LIB
default y
---help---
Allow the system to enter sleep states in which main memory is
@@ -28,6 +29,15 @@ config SUSPEND_SKIP_SYNC
of suspend, or they are content with invoking sync() from
user-space before invoking suspend. Say Y if that's your case.
+config WAKELOCK
+ bool "Android's method of preventing suspend"
+ default y
+ ---help---
+ This allows applications to prevent the CPU from suspending while
+ they need it.
+
+ Say Y if you are running an android userspace.
+
config HIBERNATE_CALLBACKS
bool
@@ -105,6 +115,7 @@ config PM_SLEEP
def_bool y
depends on SUSPEND || HIBERNATE_CALLBACKS
select PM
+ select SRCU
config PM_SLEEP_SMP
def_bool y
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index cb880a14cc39..22eb9ed879ad 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -12,3 +12,5 @@ obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o
obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o
obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o
+
+obj-$(CONFIG_SUSPEND) += wakeup_reason.o
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 3124cebaec31..797f19e2aaa9 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -647,7 +647,7 @@ static void power_down(void)
*/
int hibernate(void)
{
- int error;
+ int error, nr_calls = 0;
if (!hibernation_available()) {
pr_debug("PM: Hibernation not available.\n");
@@ -662,9 +662,11 @@ int hibernate(void)
}
pm_prepare_console();
- error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
- if (error)
+ error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
+ if (error) {
+ nr_calls--;
goto Exit;
+ }
printk(KERN_INFO "PM: Syncing filesystems ... ");
sys_sync();
@@ -714,7 +716,7 @@ int hibernate(void)
/* Don't bother checking whether freezer_test_done is true */
freezer_test_done = false;
Exit:
- pm_notifier_call_chain(PM_POST_HIBERNATION);
+ __pm_notifier_call_chain(PM_POST_HIBERNATION, nr_calls, NULL);
pm_restore_console();
atomic_inc(&snapshot_device_available);
Unlock:
@@ -740,7 +742,7 @@ int hibernate(void)
*/
static int software_resume(void)
{
- int error;
+ int error, nr_calls = 0;
unsigned int flags;
/*
@@ -827,9 +829,11 @@ static int software_resume(void)
}
pm_prepare_console();
- error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
- if (error)
+ error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
+ if (error) {
+ nr_calls--;
goto Close_Finish;
+ }
pr_debug("PM: Preparing processes for restore.\n");
error = freeze_processes();
@@ -855,7 +859,7 @@ static int software_resume(void)
unlock_device_hotplug();
thaw_processes();
Finish:
- pm_notifier_call_chain(PM_POST_RESTORE);
+ __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
pm_restore_console();
atomic_inc(&snapshot_device_available);
/* For success case, the suspend path will release the lock */
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b2dd4d999900..68c0eaae8034 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -38,12 +38,19 @@ int unregister_pm_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL_GPL(unregister_pm_notifier);
-int pm_notifier_call_chain(unsigned long val)
+int __pm_notifier_call_chain(unsigned long val, int nr_to_call, int *nr_calls)
{
- int ret = blocking_notifier_call_chain(&pm_chain_head, val, NULL);
+ int ret;
+
+ ret = __blocking_notifier_call_chain(&pm_chain_head, val, NULL,
+ nr_to_call, nr_calls);
return notifier_to_errno(ret);
}
+int pm_notifier_call_chain(unsigned long val)
+{
+ return __pm_notifier_call_chain(val, -1, NULL);
+}
/* If set, devices may be suspended and resumed asynchronously. */
int pm_async_enabled = 1;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index caadb566e82b..436e302eb024 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -85,9 +85,6 @@ extern int in_suspend;
extern dev_t swsusp_resume_device;
extern sector_t swsusp_resume_block;
-extern asmlinkage int swsusp_arch_suspend(void);
-extern asmlinkage int swsusp_arch_resume(void);
-
extern int create_basic_memory_bitmaps(void);
extern void free_basic_memory_bitmaps(void);
extern int hibernate_preallocate_memory(void);
@@ -191,6 +188,8 @@ static inline void suspend_test_finish(const char *label) {}
#ifdef CONFIG_PM_SLEEP
/* kernel/power/main.c */
+extern int __pm_notifier_call_chain(unsigned long val, int nr_to_call,
+ int *nr_calls);
extern int pm_notifier_call_chain(unsigned long val);
#endif
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 564f786df470..cc177142a08f 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -18,8 +18,10 @@
#include <linux/workqueue.h>
#include <linux/kmod.h>
#include <trace/events/power.h>
+#include <linux/wakeup_reason.h>
+#include <linux/cpuset.h>
-/*
+/*
* Timeout for stopping processes
*/
unsigned int __read_mostly freeze_timeout_msecs = 20 * MSEC_PER_SEC;
@@ -35,6 +37,9 @@ static int try_to_freeze_tasks(bool user_only)
unsigned int elapsed_msecs;
bool wakeup = false;
int sleep_usecs = USEC_PER_MSEC;
+#ifdef CONFIG_PM_SLEEP
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
+#endif
do_gettimeofday(&start);
@@ -64,6 +69,11 @@ static int try_to_freeze_tasks(bool user_only)
break;
if (pm_wakeup_pending()) {
+#ifdef CONFIG_PM_SLEEP
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
+#endif
wakeup = true;
break;
}
@@ -83,15 +93,17 @@ static int try_to_freeze_tasks(bool user_only)
do_div(elapsed_msecs64, NSEC_PER_MSEC);
elapsed_msecs = elapsed_msecs64;
- if (todo) {
+ if (wakeup) {
+ pr_cont("\n");
+ pr_err("Freezing of tasks aborted after %d.%03d seconds",
+ elapsed_msecs / 1000, elapsed_msecs % 1000);
+ } else if (todo) {
pr_cont("\n");
- pr_err("Freezing of tasks %s after %d.%03d seconds "
- "(%d tasks refusing to freeze, wq_busy=%d):\n",
- wakeup ? "aborted" : "failed",
+ pr_err("Freezing of tasks failed after %d.%03d seconds"
+ " (%d tasks refusing to freeze, wq_busy=%d):\n",
elapsed_msecs / 1000, elapsed_msecs % 1000,
todo - wq_busy, wq_busy);
- if (!wakeup) {
read_lock(&tasklist_lock);
for_each_process_thread(g, p) {
if (p != current && !freezer_should_skip(p)
@@ -99,7 +111,6 @@ static int try_to_freeze_tasks(bool user_only)
sched_show_task(p);
}
read_unlock(&tasklist_lock);
- }
} else {
pr_cont("(elapsed %d.%03d seconds) ", elapsed_msecs / 1000,
elapsed_msecs % 1000);
@@ -198,6 +209,8 @@ void thaw_processes(void)
__usermodehelper_set_disable_depth(UMH_FREEZING);
thaw_workqueues();
+ cpuset_wait_for_hotplug();
+
read_lock(&tasklist_lock);
for_each_process_thread(g, p) {
/* No other threads should have PF_SUSPEND_TASK set */
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f9fe133c13e2..58209d8bfc56 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -26,9 +26,11 @@
#include <linux/suspend.h>
#include <linux/syscore_ops.h>
#include <linux/ftrace.h>
+#include <linux/rtc.h>
#include <trace/events/power.h>
#include <linux/compiler.h>
#include <linux/moduleparam.h>
+#include <linux/wakeup_reason.h>
#include "power.h"
@@ -266,16 +268,18 @@ static int suspend_test(int level)
*/
static int suspend_prepare(suspend_state_t state)
{
- int error;
+ int error, nr_calls = 0;
if (!sleep_state_supported(state))
return -EPERM;
pm_prepare_console();
- error = pm_notifier_call_chain(PM_SUSPEND_PREPARE);
- if (error)
+ error = __pm_notifier_call_chain(PM_SUSPEND_PREPARE, -1, &nr_calls);
+ if (error) {
+ nr_calls--;
goto Finish;
+ }
trace_suspend_resume(TPS("freeze_processes"), 0, true);
error = suspend_freeze_processes();
@@ -286,7 +290,7 @@ static int suspend_prepare(suspend_state_t state)
suspend_stats.failed_freeze++;
dpm_save_failed_step(SUSPEND_FREEZE);
Finish:
- pm_notifier_call_chain(PM_POST_SUSPEND);
+ __pm_notifier_call_chain(PM_POST_SUSPEND, nr_calls, NULL);
pm_restore_console();
return error;
}
@@ -312,7 +316,8 @@ void __weak arch_suspend_enable_irqs(void)
*/
static int suspend_enter(suspend_state_t state, bool *wakeup)
{
- int error;
+ char suspend_abort[MAX_SUSPEND_ABORT_LEN];
+ int error, last_dev;
error = platform_suspend_prepare(state);
if (error)
@@ -320,7 +325,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
error = dpm_suspend_late(PMSG_SUSPEND);
if (error) {
+ last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+ last_dev %= REC_FAILED_NUM;
printk(KERN_ERR "PM: late suspend of devices failed\n");
+ log_suspend_abort_reason("%s device failed to power down",
+ suspend_stats.failed_devs[last_dev]);
goto Platform_finish;
}
error = platform_suspend_prepare_late(state);
@@ -329,7 +338,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
error = dpm_suspend_noirq(PMSG_SUSPEND);
if (error) {
+ last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1;
+ last_dev %= REC_FAILED_NUM;
printk(KERN_ERR "PM: noirq suspend of devices failed\n");
+ log_suspend_abort_reason("noirq suspend of %s device failed",
+ suspend_stats.failed_devs[last_dev]);
goto Platform_early_resume;
}
error = platform_suspend_prepare_noirq(state);
@@ -353,8 +366,10 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
}
error = disable_nonboot_cpus();
- if (error || suspend_test(TEST_CPUS))
+ if (error || suspend_test(TEST_CPUS)) {
+ log_suspend_abort_reason("Disabling non-boot cpus failed");
goto Enable_cpus;
+ }
arch_suspend_disable_irqs();
BUG_ON(!irqs_disabled());
@@ -370,6 +385,9 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
state, false);
events_check_enabled = false;
} else if (*wakeup) {
+ pm_get_active_wakeup_sources(suspend_abort,
+ MAX_SUSPEND_ABORT_LEN);
+ log_suspend_abort_reason(suspend_abort);
error = -EBUSY;
}
syscore_resume();
@@ -417,6 +435,7 @@ int suspend_devices_and_enter(suspend_state_t state)
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
pr_err("PM: Some devices failed to suspend, or early wake event detected\n");
+ log_suspend_abort_reason("Some devices failed to suspend, or early wake event detected");
goto Recover_platform;
}
suspend_test_finish("suspend devices");
@@ -518,6 +537,18 @@ static int enter_state(suspend_state_t state)
return error;
}
+static void pm_suspend_marker(char *annotation)
+{
+ struct timespec ts;
+ struct rtc_time tm;
+
+ getnstimeofday(&ts);
+ rtc_time_to_tm(ts.tv_sec, &tm);
+ pr_info("PM: suspend %s %d-%02d-%02d %02d:%02d:%02d.%09lu UTC\n",
+ annotation, tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+ tm.tm_hour, tm.tm_min, tm.tm_sec, ts.tv_nsec);
+}
+
/**
* pm_suspend - Externally visible function for suspending the system.
* @state: System sleep state to enter.
@@ -532,6 +563,7 @@ int pm_suspend(suspend_state_t state)
if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
return -EINVAL;
+ pm_suspend_marker("entry");
error = enter_state(state);
if (error) {
suspend_stats.fail++;
@@ -539,6 +571,7 @@ int pm_suspend(suspend_state_t state)
} else {
suspend_stats.success++;
}
+ pm_suspend_marker("exit");
return error;
}
EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index 084452e34a12..bdff5ed57f10 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -203,8 +203,10 @@ static int __init test_suspend(void)
/* RTCs have initialized by now too ... can we use one? */
dev = class_find_device(rtc_class, NULL, NULL, has_wakealarm);
- if (dev)
+ if (dev) {
rtc = rtc_class_open(dev_name(dev));
+ put_device(dev);
+ }
if (!rtc) {
printk(warn_no_rtc);
return 0;
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 12cd989dadf6..160e1006640d 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -37,6 +37,14 @@
#define HIBERNATE_SIG "S1SUSPEND"
/*
+ * When reading an {un,}compressed image, we may restore pages in place,
+ * in which case some architectures need these pages cleaning before they
+ * can be executed. We don't know which pages these may be, so clean the lot.
+ */
+static bool clean_pages_on_read;
+static bool clean_pages_on_decompress;
+
+/*
* The swap map is a data structure used for keeping track of each page
* written to a swap partition. It consists of many swap_map_page
* structures that contain each an array of MAP_PAGE_ENTRIES swap entries.
@@ -241,6 +249,9 @@ static void hib_end_io(struct bio *bio)
if (bio_data_dir(bio) == WRITE)
put_page(page);
+ else if (clean_pages_on_read)
+ flush_icache_range((unsigned long)page_address(page),
+ (unsigned long)page_address(page) + PAGE_SIZE);
if (bio->bi_error && !hb->error)
hb->error = bio->bi_error;
@@ -1049,6 +1060,7 @@ static int load_image(struct swap_map_handle *handle,
hib_init_batch(&hb);
+ clean_pages_on_read = true;
printk(KERN_INFO "PM: Loading image data pages (%u pages)...\n",
nr_to_read);
m = nr_to_read / 10;
@@ -1124,6 +1136,10 @@ static int lzo_decompress_threadfn(void *data)
d->unc_len = LZO_UNC_SIZE;
d->ret = lzo1x_decompress_safe(d->cmp + LZO_HEADER, d->cmp_len,
d->unc, &d->unc_len);
+ if (clean_pages_on_decompress)
+ flush_icache_range((unsigned long)d->unc,
+ (unsigned long)d->unc + d->unc_len);
+
atomic_set(&d->stop, 1);
wake_up(&d->done);
}
@@ -1189,6 +1205,8 @@ static int load_image_lzo(struct swap_map_handle *handle,
}
memset(crc, 0, offsetof(struct crc_data, go));
+ clean_pages_on_decompress = true;
+
/*
* Start the decompression threads.
*/
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 526e8911460a..bc6dde1f1567 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -47,7 +47,7 @@ atomic_t snapshot_device_available = ATOMIC_INIT(1);
static int snapshot_open(struct inode *inode, struct file *filp)
{
struct snapshot_data *data;
- int error;
+ int error, nr_calls = 0;
if (!hibernation_available())
return -EPERM;
@@ -74,9 +74,9 @@ static int snapshot_open(struct inode *inode, struct file *filp)
swap_type_of(swsusp_resume_device, 0, NULL) : -1;
data->mode = O_RDONLY;
data->free_bitmaps = false;
- error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE);
+ error = __pm_notifier_call_chain(PM_HIBERNATION_PREPARE, -1, &nr_calls);
if (error)
- pm_notifier_call_chain(PM_POST_HIBERNATION);
+ __pm_notifier_call_chain(PM_POST_HIBERNATION, --nr_calls, NULL);
} else {
/*
* Resuming. We may need to wait for the image device to
@@ -86,13 +86,15 @@ static int snapshot_open(struct inode *inode, struct file *filp)
data->swap = -1;
data->mode = O_WRONLY;
- error = pm_notifier_call_chain(PM_RESTORE_PREPARE);
+ error = __pm_notifier_call_chain(PM_RESTORE_PREPARE, -1, &nr_calls);
if (!error) {
error = create_basic_memory_bitmaps();
data->free_bitmaps = !error;
- }
+ } else
+ nr_calls--;
+
if (error)
- pm_notifier_call_chain(PM_POST_RESTORE);
+ __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL);
}
if (error)
atomic_inc(&snapshot_device_available);
@@ -184,6 +186,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
res = PAGE_SIZE - pg_offp;
}
+ if (!data_of(data->handle)) {
+ res = -EINVAL;
+ goto unlock;
+ }
+
res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp,
buf, count);
if (res > 0)
diff --git a/kernel/power/wakeup_reason.c b/kernel/power/wakeup_reason.c
new file mode 100644
index 000000000000..252611fad2fe
--- /dev/null
+++ b/kernel/power/wakeup_reason.c
@@ -0,0 +1,225 @@
+/*
+ * kernel/power/wakeup_reason.c
+ *
+ * Logs the reasons which caused the kernel to resume from
+ * the suspend mode.
+ *
+ * Copyright (C) 2014 Google, Inc.
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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.
+ */
+
+#include <linux/wakeup_reason.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+
+
+#define MAX_WAKEUP_REASON_IRQS 32
+static int irq_list[MAX_WAKEUP_REASON_IRQS];
+static int irqcount;
+static bool suspend_abort;
+static char abort_reason[MAX_SUSPEND_ABORT_LEN];
+static struct kobject *wakeup_reason;
+static DEFINE_SPINLOCK(resume_reason_lock);
+
+static ktime_t last_monotime; /* monotonic time before last suspend */
+static ktime_t curr_monotime; /* monotonic time after last suspend */
+static ktime_t last_stime; /* monotonic boottime offset before last suspend */
+static ktime_t curr_stime; /* monotonic boottime offset after last suspend */
+
+static ssize_t last_resume_reason_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ int irq_no, buf_offset = 0;
+ struct irq_desc *desc;
+ spin_lock(&resume_reason_lock);
+ if (suspend_abort) {
+ buf_offset = sprintf(buf, "Abort: %s", abort_reason);
+ } else {
+ for (irq_no = 0; irq_no < irqcount; irq_no++) {
+ desc = irq_to_desc(irq_list[irq_no]);
+ if (desc && desc->action && desc->action->name)
+ buf_offset += sprintf(buf + buf_offset, "%d %s\n",
+ irq_list[irq_no], desc->action->name);
+ else
+ buf_offset += sprintf(buf + buf_offset, "%d\n",
+ irq_list[irq_no]);
+ }
+ }
+ spin_unlock(&resume_reason_lock);
+ return buf_offset;
+}
+
+static ssize_t last_suspend_time_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct timespec sleep_time;
+ struct timespec total_time;
+ struct timespec suspend_resume_time;
+
+ /*
+ * total_time is calculated from monotonic bootoffsets because
+ * unlike CLOCK_MONOTONIC it include the time spent in suspend state.
+ */
+ total_time = ktime_to_timespec(ktime_sub(curr_stime, last_stime));
+
+ /*
+ * suspend_resume_time is calculated as monotonic (CLOCK_MONOTONIC)
+ * time interval before entering suspend and post suspend.
+ */
+ suspend_resume_time = ktime_to_timespec(ktime_sub(curr_monotime, last_monotime));
+
+ /* sleep_time = total_time - suspend_resume_time */
+ sleep_time = timespec_sub(total_time, suspend_resume_time);
+
+ /* Export suspend_resume_time and sleep_time in pair here. */
+ return sprintf(buf, "%lu.%09lu %lu.%09lu\n",
+ suspend_resume_time.tv_sec, suspend_resume_time.tv_nsec,
+ sleep_time.tv_sec, sleep_time.tv_nsec);
+}
+
+static struct kobj_attribute resume_reason = __ATTR_RO(last_resume_reason);
+static struct kobj_attribute suspend_time = __ATTR_RO(last_suspend_time);
+
+static struct attribute *attrs[] = {
+ &resume_reason.attr,
+ &suspend_time.attr,
+ NULL,
+};
+static struct attribute_group attr_group = {
+ .attrs = attrs,
+};
+
+/*
+ * logs all the wake up reasons to the kernel
+ * stores the irqs to expose them to the userspace via sysfs
+ */
+void log_wakeup_reason(int irq)
+{
+ struct irq_desc *desc;
+ desc = irq_to_desc(irq);
+ if (desc && desc->action && desc->action->name)
+ printk(KERN_INFO "Resume caused by IRQ %d, %s\n", irq,
+ desc->action->name);
+ else
+ printk(KERN_INFO "Resume caused by IRQ %d\n", irq);
+
+ spin_lock(&resume_reason_lock);
+ if (irqcount == MAX_WAKEUP_REASON_IRQS) {
+ spin_unlock(&resume_reason_lock);
+ printk(KERN_WARNING "Resume caused by more than %d IRQs\n",
+ MAX_WAKEUP_REASON_IRQS);
+ return;
+ }
+
+ irq_list[irqcount++] = irq;
+ spin_unlock(&resume_reason_lock);
+}
+
+int check_wakeup_reason(int irq)
+{
+ int irq_no;
+ int ret = false;
+
+ spin_lock(&resume_reason_lock);
+ for (irq_no = 0; irq_no < irqcount; irq_no++)
+ if (irq_list[irq_no] == irq) {
+ ret = true;
+ break;
+ }
+ spin_unlock(&resume_reason_lock);
+ return ret;
+}
+
+void log_suspend_abort_reason(const char *fmt, ...)
+{
+ va_list args;
+
+ spin_lock(&resume_reason_lock);
+
+ //Suspend abort reason has already been logged.
+ if (suspend_abort) {
+ spin_unlock(&resume_reason_lock);
+ return;
+ }
+
+ suspend_abort = true;
+ va_start(args, fmt);
+ vsnprintf(abort_reason, MAX_SUSPEND_ABORT_LEN, fmt, args);
+ va_end(args);
+ spin_unlock(&resume_reason_lock);
+}
+
+/* Detects a suspend and clears all the previous wake up reasons*/
+static int wakeup_reason_pm_event(struct notifier_block *notifier,
+ unsigned long pm_event, void *unused)
+{
+ switch (pm_event) {
+ case PM_SUSPEND_PREPARE:
+ spin_lock(&resume_reason_lock);
+ irqcount = 0;
+ suspend_abort = false;
+ spin_unlock(&resume_reason_lock);
+ /* monotonic time since boot */
+ last_monotime = ktime_get();
+ /* monotonic time since boot including the time spent in suspend */
+ last_stime = ktime_get_boottime();
+ break;
+ case PM_POST_SUSPEND:
+ /* monotonic time since boot */
+ curr_monotime = ktime_get();
+ /* monotonic time since boot including the time spent in suspend */
+ curr_stime = ktime_get_boottime();
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block wakeup_reason_pm_notifier_block = {
+ .notifier_call = wakeup_reason_pm_event,
+};
+
+/* Initializes the sysfs parameter
+ * registers the pm_event notifier
+ */
+int __init wakeup_reason_init(void)
+{
+ int retval;
+
+ retval = register_pm_notifier(&wakeup_reason_pm_notifier_block);
+ if (retval)
+ printk(KERN_WARNING "[%s] failed to register PM notifier %d\n",
+ __func__, retval);
+
+ wakeup_reason = kobject_create_and_add("wakeup_reasons", kernel_kobj);
+ if (!wakeup_reason) {
+ printk(KERN_WARNING "[%s] failed to create a sysfs kobject\n",
+ __func__);
+ return 1;
+ }
+ retval = sysfs_create_group(wakeup_reason, &attr_group);
+ if (retval) {
+ kobject_put(wakeup_reason);
+ printk(KERN_WARNING "[%s] failed to create a sysfs group %d\n",
+ __func__, retval);
+ }
+ return 0;
+}
+
+late_initcall(wakeup_reason_init);
diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c
index d5760c42f042..61d41ca41844 100644
--- a/kernel/printk/braille.c
+++ b/kernel/printk/braille.c
@@ -2,12 +2,13 @@
#include <linux/kernel.h>
#include <linux/console.h>
+#include <linux/errno.h>
#include <linux/string.h>
#include "console_cmdline.h"
#include "braille.h"
-char *_braille_console_setup(char **str, char **brl_options)
+int _braille_console_setup(char **str, char **brl_options)
{
if (!strncmp(*str, "brl,", 4)) {
*brl_options = "";
@@ -15,14 +16,14 @@ char *_braille_console_setup(char **str, char **brl_options)
} else if (!strncmp(*str, "brl=", 4)) {
*brl_options = *str + 4;
*str = strchr(*brl_options, ',');
- if (!*str)
+ if (!*str) {
pr_err("need port name after brl=\n");
- else
- *((*str)++) = 0;
- } else
- return NULL;
+ return -EINVAL;
+ }
+ *((*str)++) = 0;
+ }
- return *str;
+ return 0;
}
int
diff --git a/kernel/printk/braille.h b/kernel/printk/braille.h
index 769d771145c8..749a6756843a 100644
--- a/kernel/printk/braille.h
+++ b/kernel/printk/braille.h
@@ -9,7 +9,14 @@ braille_set_options(struct console_cmdline *c, char *brl_options)
c->brl_options = brl_options;
}
-char *
+/*
+ * Setup console according to braille options.
+ * Return -EINVAL on syntax error, 0 on success (or no braille option was
+ * actually given).
+ * Modifies str to point to the serial options
+ * Sets brl_options to the parsed braille options.
+ */
+int
_braille_console_setup(char **str, char **brl_options);
int
@@ -25,10 +32,10 @@ braille_set_options(struct console_cmdline *c, char *brl_options)
{
}
-static inline char *
+static inline int
_braille_console_setup(char **str, char **brl_options)
{
- return NULL;
+ return 0;
}
static inline int
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c048e34b177f..62ffd417622c 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -55,6 +55,10 @@
#include "console_cmdline.h"
#include "braille.h"
+#ifdef CONFIG_EARLY_PRINTK_DIRECT
+extern void printascii(char *);
+#endif
+
int console_printk[4] = {
CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */
MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */
@@ -881,7 +885,12 @@ static void __init log_buf_len_update(unsigned size)
/* save requested log_buf_len since it's too early to process it */
static int __init log_buf_len_setup(char *str)
{
- unsigned size = memparse(str, &str);
+ unsigned int size;
+
+ if (!str)
+ return -EINVAL;
+
+ size = memparse(str, &str);
log_buf_len_update(size);
@@ -1436,7 +1445,7 @@ static void call_console_drivers(int level,
{
struct console *con;
- trace_console(text, len);
+ trace_console_rcuidle(text, len);
if (level >= console_loglevel && !ignore_loglevel)
return;
@@ -1754,6 +1763,10 @@ asmlinkage int vprintk_emit(int facility, int level,
}
}
+#ifdef CONFIG_EARLY_PRINTK_DIRECT
+ printascii(text);
+#endif
+
if (level == LOGLEVEL_DEFAULT)
level = default_message_loglevel;
@@ -3168,9 +3181,8 @@ void show_regs_print_info(const char *log_lvl)
{
dump_stack_print_info(log_lvl);
- printk("%stask: %p ti: %p task.ti: %p\n",
- log_lvl, current, current_thread_info(),
- task_thread_info(current));
+ printk("%stask: %p task.stack: %p\n",
+ log_lvl, current, task_stack_page(current));
}
#endif
diff --git a/kernel/profile.c b/kernel/profile.c
index 99513e1160e5..9cd8e18e6f18 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -44,7 +44,7 @@ int prof_on __read_mostly;
EXPORT_SYMBOL_GPL(prof_on);
static cpumask_var_t prof_cpu_mask;
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS)
static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
static DEFINE_PER_CPU(int, cpu_profile_flip);
static DEFINE_MUTEX(profile_flip_mutex);
@@ -201,7 +201,7 @@ int profile_event_unregister(enum profile_type type, struct notifier_block *n)
}
EXPORT_SYMBOL_GPL(profile_event_unregister);
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS)
/*
* Each cpu has a pair of open-addressed hashtables for pending
* profile hits. read_profile() IPI's all cpus to request them
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 3189e51db7e8..8303874c2a06 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -28,17 +28,26 @@
#include <linux/compat.h>
+void __ptrace_link(struct task_struct *child, struct task_struct *new_parent,
+ const struct cred *ptracer_cred)
+{
+ BUG_ON(!list_empty(&child->ptrace_entry));
+ list_add(&child->ptrace_entry, &new_parent->ptraced);
+ child->parent = new_parent;
+ child->ptracer_cred = get_cred(ptracer_cred);
+}
+
/*
* ptrace a task: make the debugger its new parent and
* move it to the ptrace list.
*
* Must be called with the tasklist lock write-held.
*/
-void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
+static void ptrace_link(struct task_struct *child, struct task_struct *new_parent)
{
- BUG_ON(!list_empty(&child->ptrace_entry));
- list_add(&child->ptrace_entry, &new_parent->ptraced);
- child->parent = new_parent;
+ rcu_read_lock();
+ __ptrace_link(child, new_parent, __task_cred(new_parent));
+ rcu_read_unlock();
}
/**
@@ -71,11 +80,15 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
*/
void __ptrace_unlink(struct task_struct *child)
{
+ const struct cred *old_cred;
BUG_ON(!child->ptrace);
child->ptrace = 0;
child->parent = child->real_parent;
list_del_init(&child->ptrace_entry);
+ old_cred = child->ptracer_cred;
+ child->ptracer_cred = NULL;
+ put_cred(old_cred);
spin_lock(&child->sighand->siglock);
@@ -144,11 +157,17 @@ static void ptrace_unfreeze_traced(struct task_struct *task)
WARN_ON(!task->ptrace || task->parent != current);
+ /*
+ * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
+ * Recheck state under the lock to close this race.
+ */
spin_lock_irq(&task->sighand->siglock);
- if (__fatal_signal_pending(task))
- wake_up_state(task, __TASK_TRACED);
- else
- task->state = TASK_TRACED;
+ if (task->state == __TASK_TRACED) {
+ if (__fatal_signal_pending(task))
+ wake_up_state(task, __TASK_TRACED);
+ else
+ task->state = TASK_TRACED;
+ }
spin_unlock_irq(&task->sighand->siglock);
}
@@ -209,6 +228,9 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
{
+ if (mode & PTRACE_MODE_SCHED)
+ return false;
+
if (mode & PTRACE_MODE_NOAUDIT)
return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
else
@@ -219,7 +241,7 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
{
const struct cred *cred = current_cred(), *tcred;
- int dumpable = 0;
+ struct mm_struct *mm;
kuid_t caller_uid;
kgid_t caller_gid;
@@ -270,20 +292,22 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
return -EPERM;
ok:
rcu_read_unlock();
- smp_rmb();
- if (task->mm)
- dumpable = get_dumpable(task->mm);
- rcu_read_lock();
- if (dumpable != SUID_DUMP_USER &&
- !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
- rcu_read_unlock();
- return -EPERM;
- }
- rcu_read_unlock();
+ mm = task->mm;
+ if (mm &&
+ ((get_dumpable(mm) != SUID_DUMP_USER) &&
+ !ptrace_has_cap(mm->user_ns, mode)))
+ return -EPERM;
+ if (mode & PTRACE_MODE_SCHED)
+ return 0;
return security_ptrace_access_check(task, mode);
}
+bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode)
+{
+ return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED);
+}
+
bool ptrace_may_access(struct task_struct *task, unsigned int mode)
{
int err;
@@ -343,13 +367,9 @@ static int ptrace_attach(struct task_struct *task, long request,
if (seize)
flags |= PT_SEIZED;
- rcu_read_lock();
- if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE))
- flags |= PT_PTRACE_CAP;
- rcu_read_unlock();
task->ptrace = flags;
- __ptrace_link(task, current);
+ ptrace_link(task, current);
/* SEIZE doesn't trap tracee on attach */
if (!seize)
@@ -416,7 +436,7 @@ static int ptrace_traceme(void)
*/
if (!ret && !(current->real_parent->flags & PF_EXITING)) {
current->ptrace = PT_PTRACED;
- __ptrace_link(current, current->real_parent);
+ ptrace_link(current, current->real_parent);
}
}
write_unlock_irq(&tasklist_lock);
diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile
index 61a16569ffbf..032b2c015beb 100644
--- a/kernel/rcu/Makefile
+++ b/kernel/rcu/Makefile
@@ -1,3 +1,7 @@
+# Any varying coverage in these files is non-deterministic
+# and is generally not a function of system call inputs.
+KCOV_INSTRUMENT := n
+
obj-y += update.o sync.o
obj-$(CONFIG_SRCU) += srcu.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c
index be922c9f3d37..b49cf3ac2d47 100644
--- a/kernel/rcu/sync.c
+++ b/kernel/rcu/sync.c
@@ -68,6 +68,7 @@ void rcu_sync_lockdep_assert(struct rcu_sync *rsp)
RCU_LOCKDEP_WARN(!gp_ops[rsp->gp_type].held(),
"suspicious rcu_sync_is_idle() usage");
}
+EXPORT_SYMBOL_GPL(rcu_sync_lockdep_assert);
#endif
/**
@@ -83,6 +84,18 @@ void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type)
}
/**
+ * Must be called after rcu_sync_init() and before first use.
+ *
+ * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}()
+ * pairs turn into NO-OPs.
+ */
+void rcu_sync_enter_start(struct rcu_sync *rsp)
+{
+ rsp->gp_count++;
+ rsp->gp_state = GP_PASSED;
+}
+
+/**
* rcu_sync_enter() - Force readers onto slowpath
* @rsp: Pointer to rcu_sync structure to use for synchronization
*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f07343b54fe5..082aedefe29c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -759,6 +759,12 @@ void rcu_irq_exit(void)
local_irq_save(flags);
rdtp = this_cpu_ptr(&rcu_dynticks);
+
+ /* Page faults can happen in NMI handlers, so check... */
+ if (READ_ONCE(rdtp->dynticks_nmi_nesting))
+ return;
+
+ RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting--;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -887,6 +893,12 @@ void rcu_irq_enter(void)
local_irq_save(flags);
rdtp = this_cpu_ptr(&rcu_dynticks);
+
+ /* Page faults can happen in NMI handlers, so check... */
+ if (READ_ONCE(rdtp->dynticks_nmi_nesting))
+ return;
+
+ RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!");
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting++;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -1599,15 +1611,23 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
}
/*
- * Awaken the grace-period kthread for the specified flavor of RCU.
- * Don't do a self-awaken, and don't bother awakening when there is
- * nothing for the grace-period kthread to do (as in several CPUs
- * raced to awaken, and we lost), and finally don't try to awaken
- * a kthread that has not yet been created.
+ * Awaken the grace-period kthread. Don't do a self-awaken (unless in
+ * an interrupt or softirq handler), and don't bother awakening when there
+ * is nothing for the grace-period kthread to do (as in several CPUs raced
+ * to awaken, and we lost), and finally don't try to awaken a kthread that
+ * has not yet been created. If all those checks are passed, track some
+ * debug information and awaken.
+ *
+ * So why do the self-wakeup when in an interrupt or softirq handler
+ * in the grace-period kthread's context? Because the kthread might have
+ * been interrupted just as it was going to sleep, and just after the final
+ * pre-sleep check of the awaken condition. In this case, a wakeup really
+ * is required, and is therefore supplied.
*/
static void rcu_gp_kthread_wake(struct rcu_state *rsp)
{
- if (current == rsp->gp_kthread ||
+ if ((current == rsp->gp_kthread &&
+ !in_interrupt() && !in_serving_softirq()) ||
!READ_ONCE(rsp->gp_flags) ||
!rsp->gp_kthread)
return;
@@ -3805,7 +3825,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
continue;
rdp = per_cpu_ptr(rsp->rda, cpu);
pr_cont(" %d-%c%c%c", cpu,
- "O."[cpu_online(cpu)],
+ "O."[!!cpu_online(cpu)],
"o."[!!(rdp->grpmask & rnp->expmaskinit)],
"N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 630c19772630..32cbe72bf545 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2275,6 +2275,7 @@ static int rcu_nocb_kthread(void *arg)
cl++;
c++;
local_bh_enable();
+ cond_resched_rcu_qs();
list = next;
}
trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1);
diff --git a/kernel/relay.c b/kernel/relay.c
index 0b4570cfacae..f6d5f08bdfaa 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -163,7 +163,7 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan)
{
struct rchan_buf *buf;
- if (chan->n_subbufs > UINT_MAX / sizeof(size_t *))
+ if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *))
return NULL;
buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);
diff --git a/kernel/resource.c b/kernel/resource.c
index 249b1eb1e6e1..41718cd8cab5 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -105,16 +105,25 @@ static int r_show(struct seq_file *m, void *v)
{
struct resource *root = m->private;
struct resource *r = v, *p;
+ unsigned long long start, end;
int width = root->end < 0x10000 ? 4 : 8;
int depth;
for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent)
if (p->parent == root)
break;
+
+ if (file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) {
+ start = r->start;
+ end = r->end;
+ } else {
+ start = end = 0;
+ }
+
seq_printf(m, "%*s%0*llx-%0*llx : %s\n",
depth * 2, "",
- width, (unsigned long long) r->start,
- width, (unsigned long long) r->end,
+ width, start,
+ width, end,
r->name ? r->name : "<BAD>");
return 0;
}
@@ -602,7 +611,8 @@ static int __find_resource(struct resource *root, struct resource *old,
alloc.start = constraint->alignf(constraint->alignf_data, &avail,
size, constraint->align);
alloc.end = alloc.start + size - 1;
- if (resource_contains(&avail, &alloc)) {
+ if (alloc.start <= alloc.end &&
+ resource_contains(&avail, &alloc)) {
new->start = alloc.start;
new->end = alloc.end;
return 0;
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 67687973ce80..99378130a42f 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -2,6 +2,10 @@ ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE)
endif
+# These files are disabled because they produce non-interesting flaky coverage
+# that is not a function of syscall inputs. E.g. involuntary context switches.
+KCOV_INSTRUMENT := n
+
ifneq ($(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
@@ -14,8 +18,12 @@ endif
obj-y += core.o loadavg.o clock.o cputime.o
obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
obj-y += wait.o completion.o idle.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o energy.o
+obj-$(CONFIG_SCHED_WALT) += walt.o
obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-$(CONFIG_SCHED_TUNE) += tune.o
obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
+obj-$(CONFIG_CPU_FREQ) += cpufreq.o
+obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 750ed601ddf7..8620fd01b3d0 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -111,14 +111,11 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
{
if (tg != &root_task_group)
return false;
-
/*
- * We can only assume the task group can't go away on us if
- * autogroup_move_group() can see us on ->thread_group list.
+ * If we race with autogroup_move_group() the caller can use the old
+ * value of signal->autogroup but in this case sched_move_task() will
+ * be called again before autogroup_kref_put().
*/
- if (p->flags & PF_EXITING)
- return false;
-
return true;
}
@@ -138,13 +135,17 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
}
p->signal->autogroup = autogroup_kref_get(ag);
-
- if (!READ_ONCE(sysctl_sched_autogroup_enabled))
- goto out;
-
+ /*
+ * We can't avoid sched_move_task() after we changed signal->autogroup,
+ * this process can already run with task_group() == prev->tg or we can
+ * race with cgroup code which can read autogroup = prev under rq->lock.
+ * In the latter case for_each_thread() can not miss a migrating thread,
+ * cpu_cgroup_attach() must not be possible after cgroup_exit() and it
+ * can't be removed from thread list, we hold ->siglock.
+ */
for_each_thread(p, t)
sched_move_task(t);
-out:
+
unlock_task_sighand(p, &flags);
autogroup_kref_put(prev);
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 20253dbc8610..78ec10eee484 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -32,7 +32,7 @@
#include <linux/init.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
-#include <asm/mmu_context.h>
+#include <linux/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/completion.h>
@@ -74,6 +74,7 @@
#include <linux/binfmts.h>
#include <linux/context_tracking.h>
#include <linux/compiler.h>
+#include <linux/cpufreq_times.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
@@ -89,6 +90,7 @@
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
+#include "walt.h"
DEFINE_MUTEX(sched_domains_mutex);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -287,6 +289,18 @@ int sysctl_sched_rt_runtime = 950000;
/* cpus with isolated domains */
cpumask_var_t cpu_isolated_map;
+struct rq *
+lock_rq_of(struct task_struct *p, unsigned long *flags)
+{
+ return task_rq_lock(p, flags);
+}
+
+void
+unlock_rq_of(struct rq *rq, struct task_struct *p, unsigned long *flags)
+{
+ task_rq_unlock(rq, p, flags);
+}
+
/*
* this_rq_lock - lock this runqueue and disable interrupts.
*/
@@ -533,6 +547,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
return;
+ head->count++;
+
get_task_struct(task);
/*
@@ -542,6 +558,10 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
head->lastp = &node->next;
}
+static int
+try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags,
+ int sibling_count_hint);
+
void wake_up_q(struct wake_q_head *head)
{
struct wake_q_node *node = head->first;
@@ -556,10 +576,10 @@ void wake_up_q(struct wake_q_head *head)
task->wake_q.next = NULL;
/*
- * wake_up_process() implies a wmb() to pair with the queueing
+ * try_to_wake_up() implies a wmb() to pair with the queueing
* in wake_q_add() so as not to miss wakeups.
*/
- wake_up_process(task);
+ try_to_wake_up(task, TASK_NORMAL, 0, head->count);
put_task_struct(task);
}
}
@@ -600,9 +620,9 @@ void resched_cpu(int cpu)
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
- if (!raw_spin_trylock_irqsave(&rq->lock, flags))
- return;
- resched_curr(rq);
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ if (cpu_online(cpu) || cpu == smp_processor_id())
+ resched_curr(rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -1076,7 +1096,9 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new
dequeue_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_MIGRATING;
+ double_lock_balance(rq, cpu_rq(new_cpu));
set_task_cpu(p, new_cpu);
+ double_unlock_balance(rq, cpu_rq(new_cpu));
raw_spin_unlock(&rq->lock);
rq = cpu_rq(new_cpu);
@@ -1300,6 +1322,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
p->sched_class->migrate_task_rq(p);
p->se.nr_migrations++;
perf_event_task_migrate(p);
+
+ walt_fixup_busy_time(p, new_cpu);
}
__set_task_cpu(p, new_cpu);
@@ -1314,7 +1338,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
dst_rq = cpu_rq(cpu);
deactivate_task(src_rq, p, 0);
+ p->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(p, cpu);
+ p->on_rq = TASK_ON_RQ_QUEUED;
activate_task(dst_rq, p, 0);
check_preempt_curr(dst_rq, p, 0);
} else {
@@ -1623,12 +1649,14 @@ out:
* The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
*/
static inline
-int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
+int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags,
+ int sibling_count_hint)
{
lockdep_assert_held(&p->pi_lock);
if (p->nr_cpus_allowed > 1)
- cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
+ cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags,
+ sibling_count_hint);
/*
* In order not to call set_task_cpu() on a blocking task we need
@@ -1913,6 +1941,8 @@ static void ttwu_queue(struct task_struct *p, int cpu)
* @p: the thread to be awakened
* @state: the mask of task states that can be woken
* @wake_flags: wake modifier flags (WF_*)
+ * @sibling_count_hint: A hint at the number of threads that are being woken up
+ * in this event.
*
* Put it on the run-queue if it's not already there. The "current"
* thread is always on the run-queue (except when the actual
@@ -1924,10 +1954,15 @@ static void ttwu_queue(struct task_struct *p, int cpu)
* or @state didn't match @p's state.
*/
static int
-try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
+try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags,
+ int sibling_count_hint)
{
unsigned long flags;
int cpu, success = 0;
+#ifdef CONFIG_SMP
+ struct rq *rq;
+ u64 wallclock;
+#endif
/*
* If we are going to wake up a thread waiting for CONDITION we
@@ -2007,17 +2042,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
*/
smp_rmb();
+ rq = cpu_rq(task_cpu(p));
+
+ raw_spin_lock(&rq->lock);
+ wallclock = walt_ktime_clock();
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
+ walt_update_task_ravg(p, rq, TASK_WAKE, wallclock, 0);
+ raw_spin_unlock(&rq->lock);
+
p->sched_contributes_to_load = !!task_contributes_to_load(p);
p->state = TASK_WAKING;
if (p->sched_class->task_waking)
p->sched_class->task_waking(p);
- cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
+ cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags,
+ sibling_count_hint);
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
set_task_cpu(p, cpu);
}
+
#endif /* CONFIG_SMP */
ttwu_queue(p, cpu);
@@ -2066,8 +2111,13 @@ static void try_to_wake_up_local(struct task_struct *p)
trace_sched_waking(p);
- if (!task_on_rq_queued(p))
+ if (!task_on_rq_queued(p)) {
+ u64 wallclock = walt_ktime_clock();
+
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
+ walt_update_task_ravg(p, rq, TASK_WAKE, wallclock, 0);
ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+ }
ttwu_do_wakeup(rq, p, 0);
ttwu_stat(p, smp_processor_id(), 0);
@@ -2089,13 +2139,13 @@ out:
*/
int wake_up_process(struct task_struct *p)
{
- return try_to_wake_up(p, TASK_NORMAL, 0);
+ return try_to_wake_up(p, TASK_NORMAL, 0, 1);
}
EXPORT_SYMBOL(wake_up_process);
int wake_up_state(struct task_struct *p, unsigned int state)
{
- return try_to_wake_up(p, state, 0);
+ return try_to_wake_up(p, state, 0, 1);
}
/*
@@ -2110,6 +2160,7 @@ void __dl_clear_params(struct task_struct *p)
dl_se->dl_period = 0;
dl_se->flags = 0;
dl_se->dl_bw = 0;
+ dl_se->dl_density = 0;
dl_se->dl_throttled = 0;
dl_se->dl_new = 1;
@@ -2132,7 +2183,16 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
p->se.vruntime = 0;
+#ifdef CONFIG_SCHED_WALT
+ p->last_sleep_ts = 0;
+#endif
+
INIT_LIST_HEAD(&p->se.group_node);
+ walt_init_new_task_load(p);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ p->se.cfs_rq = NULL;
+#endif
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
@@ -2142,6 +2202,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
init_dl_task_timer(&p->dl);
__dl_clear_params(p);
+ init_rt_schedtune_timer(&p->rt);
INIT_LIST_HEAD(&p->rt.run_list);
#ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -2216,11 +2277,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
__sched_fork(clone_flags, p);
/*
- * We mark the process as running here. This guarantees that
+ * We mark the process as NEW here. This guarantees that
* nobody will actually run it, and a signal or other external
* event cannot wake it up and insert it on the runqueue either.
*/
- p->state = TASK_RUNNING;
+ p->state = TASK_NEW;
/*
* Make sure we do not leak PI boosting priority to the child.
@@ -2257,8 +2318,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
p->sched_class = &fair_sched_class;
}
- if (p->sched_class->task_fork)
- p->sched_class->task_fork(p);
+ init_entity_runnable_average(&p->se);
/*
* The child is not yet in the pid-hash so no cgroup attach races,
@@ -2268,7 +2328,13 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
* Silence PROVE_RCU.
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
- set_task_cpu(p, cpu);
+ /*
+ * We're setting the cpu for the first time, we don't migrate,
+ * so use __set_task_cpu().
+ */
+ __set_task_cpu(p, cpu);
+ if (p->sched_class->task_fork)
+ p->sched_class->task_fork(p);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
#ifdef CONFIG_SCHED_INFO
@@ -2400,6 +2466,10 @@ void wake_up_new_task(struct task_struct *p)
struct rq *rq;
raw_spin_lock_irqsave(&p->pi_lock, flags);
+ p->state = TASK_RUNNING;
+
+ walt_init_new_task_load(p);
+
/* Initialize new task's runnable average */
init_entity_runnable_average(&p->se);
#ifdef CONFIG_SMP
@@ -2407,12 +2477,18 @@ void wake_up_new_task(struct task_struct *p)
* Fork balancing, do it here and not earlier because:
* - cpus_allowed can change in the fork path
* - any previously selected cpu might disappear through hotplug
+ *
+ * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
+ * as we're not fully set-up yet.
*/
- set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
+ __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0, 1));
#endif
-
rq = __task_rq_lock(p);
- activate_task(rq, p, 0);
+ update_rq_clock(rq);
+ post_init_entity_util_avg(&p->se);
+
+ walt_mark_task_starting(p);
+ activate_task(rq, p, ENQUEUE_WAKEUP_NEW);
p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p);
check_preempt_curr(rq, p, WF_FORK);
@@ -2709,7 +2785,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
- switch_mm(oldmm, mm, next);
+ switch_mm_irqs_off(oldmm, mm, next);
if (!prev->mm) {
prev->active_mm = NULL;
@@ -2793,6 +2869,36 @@ unsigned long nr_iowait_cpu(int cpu)
return atomic_read(&this->nr_iowait);
}
+#ifdef CONFIG_CPU_QUIET
+u64 nr_running_integral(unsigned int cpu)
+{
+ unsigned int seqcnt;
+ u64 integral;
+ struct rq *q;
+
+ if (cpu >= nr_cpu_ids)
+ return 0;
+
+ q = cpu_rq(cpu);
+
+ /*
+ * Update average to avoid reading stalled value if there were
+ * no run-queue changes for a long time. On the other hand if
+ * the changes are happening right now, just read current value
+ * directly.
+ */
+
+ seqcnt = read_seqcount_begin(&q->ave_seqcnt);
+ integral = do_nr_running_integral(q);
+ if (read_seqcount_retry(&q->ave_seqcnt, seqcnt)) {
+ read_seqcount_begin(&q->ave_seqcnt);
+ integral = q->nr_running_integral;
+ }
+
+ return integral;
+}
+#endif
+
void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
{
struct rq *rq = this_rq();
@@ -2813,7 +2919,7 @@ void sched_exec(void)
int dest_cpu;
raw_spin_lock_irqsave(&p->pi_lock, flags);
- dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0);
+ dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0, 1);
if (dest_cpu == smp_processor_id())
goto unlock;
@@ -2892,6 +2998,9 @@ void scheduler_tick(void)
sched_clock_tick();
raw_spin_lock(&rq->lock);
+ walt_set_window_start(rq);
+ walt_update_task_ravg(rq->curr, rq, TASK_UPDATE,
+ walt_ktime_clock(), 0);
update_rq_clock(rq);
curr->sched_class->task_tick(rq, curr, 0);
update_cpu_load_active(rq);
@@ -2905,6 +3014,9 @@ void scheduler_tick(void)
trigger_load_balance(rq);
#endif
rq_last_tick_reset(rq);
+
+ if (curr->sched_class == &fair_sched_class)
+ check_for_migration(rq, curr);
}
#ifdef CONFIG_NO_HZ_FULL
@@ -3132,6 +3244,7 @@ static void __sched notrace __schedule(bool preempt)
unsigned long *switch_count;
struct rq *rq;
int cpu;
+ u64 wallclock;
cpu = smp_processor_id();
rq = cpu_rq(cpu);
@@ -3193,11 +3306,18 @@ static void __sched notrace __schedule(bool preempt)
update_rq_clock(rq);
next = pick_next_task(rq, prev);
+ wallclock = walt_ktime_clock();
+ walt_update_task_ravg(prev, rq, PUT_PREV_TASK, wallclock, 0);
+ walt_update_task_ravg(next, rq, PICK_NEXT_TASK, wallclock, 0);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
rq->clock_skip_update = 0;
if (likely(prev != next)) {
+#ifdef CONFIG_SCHED_WALT
+ if (!prev->on_rq)
+ prev->last_sleep_ts = wallclock;
+#endif
rq->nr_switches++;
rq->curr = next;
++*switch_count;
@@ -3371,7 +3491,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
void *key)
{
- return try_to_wake_up(curr->private, mode, wake_flags);
+ return try_to_wake_up(curr->private, mode, wake_flags, 1);
}
EXPORT_SYMBOL(default_wake_function);
@@ -3397,6 +3517,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
BUG_ON(prio > MAX_PRIO);
rq = __task_rq_lock(p);
+ update_rq_clock(rq);
/*
* Idle task boosting is a nono in general. There is one
@@ -3488,6 +3609,8 @@ void set_user_nice(struct task_struct *p, long nice)
* the task might be in the middle of scheduling on another CPU.
*/
rq = task_rq_lock(p, &flags);
+ update_rq_clock(rq);
+
/*
* The RT priorities are set via sched_setscheduler(), but we still
* allow the 'normal' nice value to be set - but as expected
@@ -3648,6 +3771,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
dl_se->flags = attr->sched_flags;
dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+ dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
/*
* Changing the parameters of a task is 'tricky' and we're not doing
@@ -3820,8 +3944,8 @@ static int __sched_setscheduler(struct task_struct *p,
struct rq *rq;
int reset_on_fork;
- /* may grab non-irq protected spin_locks */
- BUG_ON(in_interrupt());
+ /* The pi code expects interrupts enabled */
+ BUG_ON(pi && in_interrupt());
recheck:
/* double check policy once rq lock held */
if (policy < 0) {
@@ -3914,6 +4038,7 @@ recheck:
* runqueue lock must be held.
*/
rq = task_rq_lock(p, &flags);
+ update_rq_clock(rq);
/*
* Changing the policy of the stop threads its a very bad idea
@@ -5019,6 +5144,7 @@ void init_idle(struct task_struct *idle, int cpu)
raw_spin_lock(&rq->lock);
__sched_fork(0, idle);
+
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
@@ -5401,9 +5527,60 @@ set_table_entry(struct ctl_table *entry,
}
static struct ctl_table *
+sd_alloc_ctl_energy_table(struct sched_group_energy *sge)
+{
+ struct ctl_table *table = sd_alloc_ctl_entry(5);
+
+ if (table == NULL)
+ return NULL;
+
+ set_table_entry(&table[0], "nr_idle_states", &sge->nr_idle_states,
+ sizeof(int), 0644, proc_dointvec_minmax, false);
+ set_table_entry(&table[1], "idle_states", &sge->idle_states[0].power,
+ sge->nr_idle_states*sizeof(struct idle_state), 0644,
+ proc_doulongvec_minmax, false);
+ set_table_entry(&table[2], "nr_cap_states", &sge->nr_cap_states,
+ sizeof(int), 0644, proc_dointvec_minmax, false);
+ set_table_entry(&table[3], "cap_states", &sge->cap_states[0].cap,
+ sge->nr_cap_states*sizeof(struct capacity_state), 0644,
+ proc_doulongvec_minmax, false);
+
+ return table;
+}
+
+static struct ctl_table *
+sd_alloc_ctl_group_table(struct sched_group *sg)
+{
+ struct ctl_table *table = sd_alloc_ctl_entry(2);
+
+ if (table == NULL)
+ return NULL;
+
+ table->procname = kstrdup("energy", GFP_KERNEL);
+ table->mode = 0555;
+ table->child = sd_alloc_ctl_energy_table((struct sched_group_energy *)sg->sge);
+
+ return table;
+}
+
+static struct ctl_table *
sd_alloc_ctl_domain_table(struct sched_domain *sd)
{
- struct ctl_table *table = sd_alloc_ctl_entry(14);
+ struct ctl_table *table;
+ unsigned int nr_entries = 14;
+
+ int i = 0;
+ struct sched_group *sg = sd->groups;
+
+ if (sg->sge) {
+ int nr_sgs = 0;
+
+ do {} while (nr_sgs++, sg = sg->next, sg != sd->groups);
+
+ nr_entries += nr_sgs;
+ }
+
+ table = sd_alloc_ctl_entry(nr_entries);
if (table == NULL)
return NULL;
@@ -5436,7 +5613,19 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[12], "name", sd->name,
CORENAME_MAX_SIZE, 0444, proc_dostring, false);
- /* &table[13] is terminator */
+ sg = sd->groups;
+ if (sg->sge) {
+ char buf[32];
+ struct ctl_table *entry = &table[13];
+
+ do {
+ snprintf(buf, 32, "group%d", i);
+ entry->procname = kstrdup(buf, GFP_KERNEL);
+ entry->mode = 0555;
+ entry->child = sd_alloc_ctl_group_table(sg);
+ } while (entry++, i++, sg = sg->next, sg != sd->groups);
+ }
+ /* &table[nr_entries-1] is terminator */
return table;
}
@@ -5552,8 +5741,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ walt_set_window_start(rq);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
rq->calc_load_update = calc_load_update;
- account_reset_rq(rq);
break;
case CPU_ONLINE:
@@ -5572,6 +5763,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
sched_ttwu_pending();
/* Update our root-domain */
raw_spin_lock_irqsave(&rq->lock, flags);
+ walt_migrate_sync_cpu(cpu);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
@@ -5609,6 +5801,10 @@ static void set_cpu_rq_start_time(void)
rq->age_stamp = sched_clock_cpu(cpu);
}
+#ifdef CONFIG_SCHED_SMT
+atomic_t sched_smt_present = ATOMIC_INIT(0);
+#endif
+
static int sched_cpu_active(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
@@ -5625,11 +5821,23 @@ static int sched_cpu_active(struct notifier_block *nfb,
* set_cpu_online(). But it might not yet have marked itself
* as active, which is essential from here on.
*/
+#ifdef CONFIG_SCHED_SMT
+ /*
+ * When going up, increment the number of cores with SMT present.
+ */
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ atomic_inc(&sched_smt_present);
+#endif
set_cpu_active(cpu, true);
stop_machine_unpark(cpu);
return NOTIFY_OK;
case CPU_DOWN_FAILED:
+#ifdef CONFIG_SCHED_SMT
+ /* Same as for CPU_ONLINE */
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ atomic_inc(&sched_smt_present);
+#endif
set_cpu_active(cpu, true);
return NOTIFY_OK;
@@ -5644,7 +5852,15 @@ static int sched_cpu_inactive(struct notifier_block *nfb,
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
set_cpu_active((long)hcpu, false);
+#ifdef CONFIG_SCHED_SMT
+ /*
+ * When going down, decrement the number of cores with SMT present.
+ */
+ if (cpumask_weight(cpu_smt_mask((long)hcpu)) == 2)
+ atomic_dec(&sched_smt_present);
+#endif
return NOTIFY_OK;
+
default:
return NOTIFY_DONE;
}
@@ -5699,9 +5915,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
if (!(sd->flags & SD_LOAD_BALANCE)) {
printk("does not load-balance\n");
- if (sd->parent)
- printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
- " has parent");
return -1;
}
@@ -5743,7 +5956,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
printk(KERN_CONT " %*pbl",
cpumask_pr_args(sched_group_cpus(group)));
if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
- printk(KERN_CONT " (cpu_capacity = %d)",
+ printk(KERN_CONT " (cpu_capacity = %lu)",
group->sgc->capacity);
}
@@ -5794,8 +6007,12 @@ static inline bool sched_debug(void)
static int sd_degenerate(struct sched_domain *sd)
{
- if (cpumask_weight(sched_domain_span(sd)) == 1)
- return 1;
+ if (cpumask_weight(sched_domain_span(sd)) == 1) {
+ if (sd->groups->sge)
+ sd->flags &= ~SD_LOAD_BALANCE;
+ else
+ return 1;
+ }
/* Following flags need at least 2 groups */
if (sd->flags & (SD_LOAD_BALANCE |
@@ -5803,8 +6020,10 @@ static int sd_degenerate(struct sched_domain *sd)
SD_BALANCE_FORK |
SD_BALANCE_EXEC |
SD_SHARE_CPUCAPACITY |
+ SD_ASYM_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
- SD_SHARE_POWERDOMAIN)) {
+ SD_SHARE_POWERDOMAIN |
+ SD_SHARE_CAP_STATES)) {
if (sd->groups != sd->groups->next)
return 0;
}
@@ -5833,10 +6052,16 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
SD_BALANCE_NEWIDLE |
SD_BALANCE_FORK |
SD_BALANCE_EXEC |
+ SD_ASYM_CPUCAPACITY |
SD_SHARE_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
SD_PREFER_SIBLING |
- SD_SHARE_POWERDOMAIN);
+ SD_SHARE_POWERDOMAIN |
+ SD_SHARE_CAP_STATES);
+ if (parent->groups->sge) {
+ parent->flags &= ~SD_LOAD_BALANCE;
+ return 0;
+ }
if (nr_node_ids == 1)
pflags &= ~SD_SERIALIZE;
}
@@ -5896,6 +6121,19 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
call_rcu_sched(&old_rd->rcu, free_rootdomain);
}
+void sched_get_rd(struct root_domain *rd)
+{
+ atomic_inc(&rd->refcount);
+}
+
+void sched_put_rd(struct root_domain *rd)
+{
+ if (!atomic_dec_and_test(&rd->refcount))
+ return;
+
+ call_rcu_sched(&rd->rcu, free_rootdomain);
+}
+
static int init_rootdomain(struct root_domain *rd)
{
memset(rd, 0, sizeof(*rd));
@@ -5909,12 +6147,23 @@ static int init_rootdomain(struct root_domain *rd)
if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
goto free_dlo_mask;
+#ifdef HAVE_RT_PUSH_IPI
+ rd->rto_cpu = -1;
+ raw_spin_lock_init(&rd->rto_lock);
+ init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
+#endif
+
init_dl_bw(&rd->dl_bw);
if (cpudl_init(&rd->cpudl) != 0)
goto free_dlo_mask;
if (cpupri_init(&rd->cpupri) != 0)
goto free_rto_mask;
+
+ init_max_cpu_capacity(&rd->max_cpu_capacity);
+
+ rd->max_cap_orig_cpu = rd->min_cap_orig_cpu = -1;
+
return 0;
free_rto_mask:
@@ -6020,11 +6269,13 @@ DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
DEFINE_PER_CPU(struct sched_domain *, sd_busy);
DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+DEFINE_PER_CPU(struct sched_domain *, sd_ea);
+DEFINE_PER_CPU(struct sched_domain *, sd_scs);
static void update_top_cache_domain(int cpu)
{
struct sched_domain *sd;
- struct sched_domain *busy_sd = NULL;
+ struct sched_domain *busy_sd = NULL, *ea_sd = NULL;
int id = cpu;
int size = 1;
@@ -6045,6 +6296,17 @@ static void update_top_cache_domain(int cpu)
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+
+ for_each_domain(cpu, sd) {
+ if (sd->groups->sge)
+ ea_sd = sd;
+ else
+ break;
+ }
+ rcu_assign_pointer(per_cpu(sd_ea, cpu), ea_sd);
+
+ sd = highest_flag_domain(cpu, SD_SHARE_CAP_STATES);
+ rcu_assign_pointer(per_cpu(sd_scs, cpu), sd);
}
/*
@@ -6123,6 +6385,9 @@ enum s_alloc {
* Build an iteration mask that can exclude certain CPUs from the upwards
* domain traversal.
*
+ * Only CPUs that can arrive at this group should be considered to continue
+ * balancing.
+ *
* Asymmetric node setups can result in situations where the domain tree is of
* unequal depth, make sure to skip domains that already cover the entire
* range.
@@ -6134,18 +6399,31 @@ enum s_alloc {
*/
static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
{
- const struct cpumask *span = sched_domain_span(sd);
+ const struct cpumask *sg_span = sched_group_cpus(sg);
struct sd_data *sdd = sd->private;
struct sched_domain *sibling;
int i;
- for_each_cpu(i, span) {
+ for_each_cpu(i, sg_span) {
sibling = *per_cpu_ptr(sdd->sd, i);
- if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+ /*
+ * Can happen in the asymmetric case, where these siblings are
+ * unused. The mask will not be empty because those CPUs that
+ * do have the top domain _should_ span the domain.
+ */
+ if (!sibling->child)
+ continue;
+
+ /* If we would not end up here, we can't continue from here */
+ if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
continue;
cpumask_set_cpu(i, sched_group_mask(sg));
}
+
+ /* We must not have empty masks here */
+ WARN_ON_ONCE(cpumask_empty(sched_group_mask(sg)));
}
/*
@@ -6205,6 +6483,8 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
* die on a /0 trap.
*/
sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+ sg->sgc->max_capacity = SCHED_CAPACITY_SCALE;
+ sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
/*
* Make sure the first group of this domain contains the
@@ -6334,6 +6614,66 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
}
/*
+ * Check that the per-cpu provided sd energy data is consistent for all cpus
+ * within the mask.
+ */
+static inline void check_sched_energy_data(int cpu, sched_domain_energy_f fn,
+ const struct cpumask *cpumask)
+{
+ const struct sched_group_energy * const sge = fn(cpu);
+ struct cpumask mask;
+ int i;
+
+ if (cpumask_weight(cpumask) <= 1)
+ return;
+
+ cpumask_xor(&mask, cpumask, get_cpu_mask(cpu));
+
+ for_each_cpu(i, &mask) {
+ const struct sched_group_energy * const e = fn(i);
+ int y;
+
+ BUG_ON(e->nr_idle_states != sge->nr_idle_states);
+
+ for (y = 0; y < (e->nr_idle_states); y++) {
+ BUG_ON(e->idle_states[y].power !=
+ sge->idle_states[y].power);
+ }
+
+ BUG_ON(e->nr_cap_states != sge->nr_cap_states);
+
+ for (y = 0; y < (e->nr_cap_states); y++) {
+ BUG_ON(e->cap_states[y].cap != sge->cap_states[y].cap);
+ BUG_ON(e->cap_states[y].power !=
+ sge->cap_states[y].power);
+ }
+ }
+}
+
+static void init_sched_energy(int cpu, struct sched_domain *sd,
+ sched_domain_energy_f fn)
+{
+ if (!(fn && fn(cpu)))
+ return;
+
+ if (cpu != group_balance_cpu(sd->groups))
+ return;
+
+ if (sd->child && !sd->child->groups->sge) {
+ pr_err("BUG: EAS setup broken for CPU%d\n", cpu);
+#ifdef CONFIG_SCHED_DEBUG
+ pr_err(" energy data on %s but not on %s domain\n",
+ sd->name, sd->child->name);
+#endif
+ return;
+ }
+
+ check_sched_energy_data(cpu, fn, sched_group_cpus(sd->groups));
+
+ sd->groups->sge = fn(cpu);
+}
+
+/*
* Initializers for schedule domains
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
*/
@@ -6437,10 +6777,19 @@ static int sched_domains_curr_level;
/*
* SD_flags allowed in topology descriptions.
*
- * SD_SHARE_CPUCAPACITY - describes SMT topologies
- * SD_SHARE_PKG_RESOURCES - describes shared caches
- * SD_NUMA - describes NUMA topologies
- * SD_SHARE_POWERDOMAIN - describes shared power domain
+ * These flags are purely descriptive of the topology and do not prescribe
+ * behaviour. Behaviour is artificial and mapped in the below sd_init()
+ * function:
+ *
+ * SD_SHARE_CPUCAPACITY - describes SMT topologies
+ * SD_SHARE_PKG_RESOURCES - describes shared caches
+ * SD_NUMA - describes NUMA topologies
+ * SD_SHARE_POWERDOMAIN - describes shared power domain
+ * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies
+ * SD_SHARE_CAP_STATES - describes shared capacity states
+ *
+ * Odd one out, which beside describing the topology has a quirk also
+ * prescribes the desired behaviour that goes along with it:
*
* Odd one out:
* SD_ASYM_PACKING - describes SMT quirks
@@ -6450,10 +6799,13 @@ static int sched_domains_curr_level;
SD_SHARE_PKG_RESOURCES | \
SD_NUMA | \
SD_ASYM_PACKING | \
- SD_SHARE_POWERDOMAIN)
+ SD_ASYM_CPUCAPACITY | \
+ SD_SHARE_POWERDOMAIN | \
+ SD_SHARE_CAP_STATES)
static struct sched_domain *
-sd_init(struct sched_domain_topology_level *tl, int cpu)
+sd_init(struct sched_domain_topology_level *tl,
+ struct sched_domain *child, int cpu)
{
struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
int sd_weight, sd_flags = 0;
@@ -6505,6 +6857,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
.smt_gain = 0,
.max_newidle_lb_cost = 0,
.next_decay_max_lb_cost = jiffies,
+ .child = child,
#ifdef CONFIG_SCHED_DEBUG
.name = tl->name,
#endif
@@ -6514,6 +6867,13 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
* Convert topological properties into behaviour.
*/
+ if (sd->flags & SD_ASYM_CPUCAPACITY) {
+ struct sched_domain *t = sd;
+
+ for_each_lower_domain(t)
+ t->flags |= SD_BALANCE_WAKE;
+ }
+
if (sd->flags & SD_SHARE_CPUCAPACITY) {
sd->flags |= SD_PREFER_SIBLING;
sd->imbalance_pct = 110;
@@ -6960,16 +7320,13 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
struct sched_domain *child, int cpu)
{
- struct sched_domain *sd = sd_init(tl, cpu);
- if (!sd)
- return child;
+ struct sched_domain *sd = sd_init(tl, child, cpu);
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
if (child) {
sd->level = child->level + 1;
sched_domain_level_max = max(sched_domain_level_max, sd->level);
child->parent = sd;
- sd->child = child;
if (!cpumask_subset(sched_domain_span(child),
sched_domain_span(sd))) {
@@ -7017,8 +7374,6 @@ static int build_sched_domains(const struct cpumask *cpu_map,
*per_cpu_ptr(d.sd, i) = sd;
if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
sd->flags |= SD_OVERLAP;
- if (cpumask_equal(cpu_map, sched_domain_span(sd)))
- break;
}
}
@@ -7038,10 +7393,13 @@ static int build_sched_domains(const struct cpumask *cpu_map,
/* Calculate CPU capacity for physical packages and nodes */
for (i = nr_cpumask_bits-1; i >= 0; i--) {
+ struct sched_domain_topology_level *tl = sched_domain_topology;
+
if (!cpumask_test_cpu(i, cpu_map))
continue;
- for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+ for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent, tl++) {
+ init_sched_energy(i, sd, tl->energy);
claim_allocations(i, sd);
init_sched_groups_capacity(i, sd);
}
@@ -7050,7 +7408,19 @@ static int build_sched_domains(const struct cpumask *cpu_map,
/* Attach the domains */
rcu_read_lock();
for_each_cpu(i, cpu_map) {
+ int max_cpu = READ_ONCE(d.rd->max_cap_orig_cpu);
+ int min_cpu = READ_ONCE(d.rd->min_cap_orig_cpu);
+
+ if ((max_cpu < 0) || (cpu_rq(i)->cpu_capacity_orig >
+ cpu_rq(max_cpu)->cpu_capacity_orig))
+ WRITE_ONCE(d.rd->max_cap_orig_cpu, i);
+
+ if ((min_cpu < 0) || (cpu_rq(i)->cpu_capacity_orig <
+ cpu_rq(min_cpu)->cpu_capacity_orig))
+ WRITE_ONCE(d.rd->min_cap_orig_cpu, i);
+
sd = *per_cpu_ptr(d.sd, i);
+
cpu_attach_domain(sd, d.rd, i);
}
rcu_read_unlock();
@@ -7271,17 +7641,16 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
* operation in the resume sequence, just build a single sched
* domain, ignoring cpusets.
*/
- num_cpus_frozen--;
- if (likely(num_cpus_frozen)) {
- partition_sched_domains(1, NULL, NULL);
+ partition_sched_domains(1, NULL, NULL);
+ if (--num_cpus_frozen)
break;
- }
/*
* This is the last CPU online operation. So fall through and
* restore the original sched domains by considering the
* cpuset configurations.
*/
+ cpuset_force_rebuild();
case CPU_ONLINE:
cpuset_update_active_cpus(true);
@@ -7462,6 +7831,7 @@ void __init sched_init(void)
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
/*
* How much cpu bandwidth does root_task_group get?
*
@@ -7503,11 +7873,17 @@ void __init sched_init(void)
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
+ rq->push_task = NULL;
rq->cpu = i;
rq->online = 0;
rq->idle_stamp = 0;
rq->avg_idle = 2*sysctl_sched_migration_cost;
rq->max_idle_balance_cost = sysctl_sched_migration_cost;
+#ifdef CONFIG_SCHED_WALT
+ rq->cur_irqload = 0;
+ rq->avg_irqload = 0;
+ rq->irqload_ts = 0;
+#endif
INIT_LIST_HEAD(&rq->cfs_tasks);
@@ -7571,6 +7947,14 @@ static inline int preempt_count_equals(int preempt_offset)
return (nested == preempt_offset);
}
+static int __might_sleep_init_called;
+int __init __might_sleep_init(void)
+{
+ __might_sleep_init_called = 1;
+ return 0;
+}
+early_initcall(__might_sleep_init);
+
void __might_sleep(const char *file, int line, int preempt_offset)
{
/*
@@ -7595,8 +7979,10 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
- !is_idle_task(current)) ||
- system_state != SYSTEM_RUNNING || oops_in_progress)
+ !is_idle_task(current)) || oops_in_progress)
+ return;
+ if (system_state != SYSTEM_RUNNING &&
+ (!__might_sleep_init_called || system_state != SYSTEM_BOOTING))
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
@@ -7782,11 +8168,9 @@ void sched_destroy_group(struct task_group *tg)
void sched_offline_group(struct task_group *tg)
{
unsigned long flags;
- int i;
/* end participation in shares distribution */
- for_each_possible_cpu(i)
- unregister_fair_sched_group(tg, i);
+ unregister_fair_sched_group(tg);
spin_lock_irqsave(&task_group_lock, flags);
list_del_rcu(&tg->list);
@@ -7794,27 +8178,9 @@ void sched_offline_group(struct task_group *tg)
spin_unlock_irqrestore(&task_group_lock, flags);
}
-/* change task's runqueue when it moves between groups.
- * The caller of this function should have put the task in its new group
- * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
- * reflect its new group.
- */
-void sched_move_task(struct task_struct *tsk)
+static void sched_change_group(struct task_struct *tsk, int type)
{
struct task_group *tg;
- int queued, running;
- unsigned long flags;
- struct rq *rq;
-
- rq = task_rq_lock(tsk, &flags);
-
- running = task_current(rq, tsk);
- queued = task_on_rq_queued(tsk);
-
- if (queued)
- dequeue_task(rq, tsk, DEQUEUE_SAVE);
- if (unlikely(running))
- put_prev_task(rq, tsk);
/*
* All callers are synchronized by task_rq_lock(); we do not use RCU
@@ -7827,11 +8193,37 @@ void sched_move_task(struct task_struct *tsk)
tsk->sched_task_group = tg;
#ifdef CONFIG_FAIR_GROUP_SCHED
- if (tsk->sched_class->task_move_group)
- tsk->sched_class->task_move_group(tsk);
+ if (tsk->sched_class->task_change_group)
+ tsk->sched_class->task_change_group(tsk, type);
else
#endif
set_task_rq(tsk, task_cpu(tsk));
+}
+
+/*
+ * Change task's runqueue when it moves between groups.
+ *
+ * The caller of this function should have put the task in its new group by
+ * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
+ * its new group.
+ */
+void sched_move_task(struct task_struct *tsk)
+{
+ int queued, running;
+ unsigned long flags;
+ struct rq *rq;
+
+ rq = task_rq_lock(tsk, &flags);
+
+ running = task_current(rq, tsk);
+ queued = task_on_rq_queued(tsk);
+
+ if (queued)
+ dequeue_task(rq, tsk, DEQUEUE_SAVE);
+ if (unlikely(running))
+ put_prev_task(rq, tsk);
+
+ sched_change_group(tsk, TASK_MOVE_GROUP);
if (unlikely(running))
tsk->sched_class->set_curr_task(rq);
@@ -8237,11 +8629,20 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
if (IS_ERR(tg))
return ERR_PTR(-ENOMEM);
- sched_online_group(tg, parent);
-
return &tg->css;
}
+/* Expose task group only after completing cgroup initialization */
+static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
+{
+ struct task_group *tg = css_tg(css);
+ struct task_group *parent = css_tg(css->parent);
+
+ if (parent)
+ sched_online_group(tg, parent);
+ return 0;
+}
+
static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
@@ -8259,15 +8660,28 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
sched_free_group(tg);
}
+/*
+ * This is called before wake_up_new_task(), therefore we really only
+ * have to set its group bits, all the other stuff does not apply.
+ */
static void cpu_cgroup_fork(struct task_struct *task, void *private)
{
- sched_move_task(task);
+ unsigned long flags;
+ struct rq *rq;
+
+ rq = task_rq_lock(task, &flags);
+
+ update_rq_clock(rq);
+ sched_change_group(task, TASK_SET_GROUP);
+
+ task_rq_unlock(rq, task, &flags);
}
static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{
struct task_struct *task;
struct cgroup_subsys_state *css;
+ int ret = 0;
cgroup_taskset_for_each(task, css, tset) {
#ifdef CONFIG_RT_GROUP_SCHED
@@ -8278,8 +8692,24 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
if (task->sched_class != &fair_sched_class)
return -EINVAL;
#endif
+ /*
+ * Serialize against wake_up_new_task() such that if its
+ * running, we're sure to observe its full state.
+ */
+ raw_spin_lock_irq(&task->pi_lock);
+ /*
+ * Avoid calling sched_move_task() before wake_up_new_task()
+ * has happened. This would lead to problems with PELT, due to
+ * move wanting to detach+attach while we're not attached yet.
+ */
+ if (task->state == TASK_NEW)
+ ret = -EINVAL;
+ raw_spin_unlock_irq(&task->pi_lock);
+
+ if (ret)
+ break;
}
- return 0;
+ return ret;
}
static void cpu_cgroup_attach(struct cgroup_taskset *tset)
@@ -8616,6 +9046,7 @@ static struct cftype cpu_files[] = {
struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
+ .css_online = cpu_cgroup_css_online,
.css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
.fork = cpu_cgroup_fork,
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
new file mode 100644
index 000000000000..dbc51442ecbc
--- /dev/null
+++ b/kernel/sched/cpufreq.c
@@ -0,0 +1,63 @@
+/*
+ * Scheduler code and data structures related to cpufreq.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "sched.h"
+
+DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_add_update_util_hook - Populate the CPU's update_util_data pointer.
+ * @cpu: The CPU to set the pointer for.
+ * @data: New pointer value.
+ * @func: Callback function to set for the CPU.
+ *
+ * Set and publish the update_util_data pointer for the given CPU.
+ *
+ * The update_util_data pointer of @cpu is set to @data and the callback
+ * function pointer in the target struct update_util_data is set to @func.
+ * That function will be called by cpufreq_update_util() from RCU-sched
+ * read-side critical sections, so it must not sleep. @data will always be
+ * passed to it as the first argument which allows the function to get to the
+ * target update_util_data structure and its container.
+ *
+ * The update_util_data pointer of @cpu must be NULL when this function is
+ * called or it will WARN() and return with no effect.
+ */
+void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data,
+ void (*func)(struct update_util_data *data, u64 time,
+ unsigned int flags))
+{
+ if (WARN_ON(!data || !func))
+ return;
+
+ if (WARN_ON(per_cpu(cpufreq_update_util_data, cpu)))
+ return;
+
+ data->func = func;
+ rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), data);
+}
+EXPORT_SYMBOL_GPL(cpufreq_add_update_util_hook);
+
+/**
+ * cpufreq_remove_update_util_hook - Clear the CPU's update_util_data pointer.
+ * @cpu: The CPU to clear the pointer for.
+ *
+ * Clear the update_util_data pointer for the given CPU.
+ *
+ * Callers must use RCU-sched callbacks to free any memory that might be
+ * accessed via the old update_util_data pointer or invoke synchronize_sched()
+ * right after this function to avoid use-after-free.
+ */
+void cpufreq_remove_update_util_hook(int cpu)
+{
+ rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL);
+}
+EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook);
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
new file mode 100644
index 000000000000..6c84b4d28914
--- /dev/null
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -0,0 +1,827 @@
+/*
+ * CPUFreq governor based on scheduler-provided CPU utilization data.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpufreq.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+#include <trace/events/power.h>
+
+#include "sched.h"
+#include "tune.h"
+
+unsigned long boosted_cpu_util(int cpu);
+
+/* Stub out fast switch routines present on mainline to reduce the backport
+ * overhead. */
+#define cpufreq_driver_fast_switch(x, y) 0
+#define cpufreq_enable_fast_switch(x)
+#define cpufreq_disable_fast_switch(x)
+#define LATENCY_MULTIPLIER (1000)
+#define SUGOV_KTHREAD_PRIORITY 50
+
+struct sugov_tunables {
+ struct gov_attr_set attr_set;
+ unsigned int up_rate_limit_us;
+ unsigned int down_rate_limit_us;
+};
+
+struct sugov_policy {
+ struct cpufreq_policy *policy;
+
+ struct sugov_tunables *tunables;
+ struct list_head tunables_hook;
+
+ raw_spinlock_t update_lock; /* For shared policies */
+ u64 last_freq_update_time;
+ s64 min_rate_limit_ns;
+ s64 up_rate_delay_ns;
+ s64 down_rate_delay_ns;
+ unsigned int next_freq;
+ unsigned int cached_raw_freq;
+
+ /* The next fields are only needed if fast switch cannot be used. */
+ struct irq_work irq_work;
+ struct kthread_work work;
+ struct mutex work_lock;
+ struct kthread_worker worker;
+ struct task_struct *thread;
+ bool work_in_progress;
+
+ bool need_freq_update;
+};
+
+struct sugov_cpu {
+ struct update_util_data update_util;
+ struct sugov_policy *sg_policy;
+
+ bool iowait_boost_pending;
+ unsigned int iowait_boost;
+ unsigned int iowait_boost_max;
+ u64 last_update;
+
+ /* The fields below are only needed when sharing a policy. */
+ unsigned long util;
+ unsigned long max;
+ unsigned int flags;
+
+ /* The field below is for single-CPU policies only. */
+#ifdef CONFIG_NO_HZ_COMMON
+ unsigned long saved_idle_calls;
+#endif
+};
+
+static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
+
+/************************ Governor internals ***********************/
+
+static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
+{
+ s64 delta_ns;
+
+ if (sg_policy->work_in_progress)
+ return false;
+
+ if (unlikely(sg_policy->need_freq_update)) {
+ sg_policy->need_freq_update = false;
+ /*
+ * This happens when limits change, so forget the previous
+ * next_freq value and force an update.
+ */
+ sg_policy->next_freq = UINT_MAX;
+ return true;
+ }
+
+ delta_ns = time - sg_policy->last_freq_update_time;
+
+ /* No need to recalculate next freq for min_rate_limit_us at least */
+ return delta_ns >= sg_policy->min_rate_limit_ns;
+}
+
+static bool sugov_up_down_rate_limit(struct sugov_policy *sg_policy, u64 time,
+ unsigned int next_freq)
+{
+ s64 delta_ns;
+
+ delta_ns = time - sg_policy->last_freq_update_time;
+
+ if (next_freq > sg_policy->next_freq &&
+ delta_ns < sg_policy->up_rate_delay_ns)
+ return true;
+
+ if (next_freq < sg_policy->next_freq &&
+ delta_ns < sg_policy->down_rate_delay_ns)
+ return true;
+
+ return false;
+}
+
+static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
+ unsigned int next_freq)
+{
+ struct cpufreq_policy *policy = sg_policy->policy;
+
+ if (sugov_up_down_rate_limit(sg_policy, time, next_freq)) {
+ /* Reset cached freq as next_freq isn't changed */
+ sg_policy->cached_raw_freq = 0;
+ return;
+ }
+
+ if (sg_policy->next_freq == next_freq)
+ return;
+
+ sg_policy->next_freq = next_freq;
+ sg_policy->last_freq_update_time = time;
+
+ if (policy->fast_switch_enabled) {
+ next_freq = cpufreq_driver_fast_switch(policy, next_freq);
+ if (next_freq == CPUFREQ_ENTRY_INVALID)
+ return;
+
+ policy->cur = next_freq;
+ trace_cpu_frequency(next_freq, smp_processor_id());
+ } else {
+ sg_policy->work_in_progress = true;
+ irq_work_queue(&sg_policy->irq_work);
+ }
+}
+
+/**
+ * get_next_freq - Compute a new frequency for a given cpufreq policy.
+ * @sg_policy: schedutil policy object to compute the new frequency for.
+ * @util: Current CPU utilization.
+ * @max: CPU capacity.
+ *
+ * If the utilization is frequency-invariant, choose the new frequency to be
+ * proportional to it, that is
+ *
+ * next_freq = C * max_freq * util / max
+ *
+ * Otherwise, approximate the would-be frequency-invariant utilization by
+ * util_raw * (curr_freq / max_freq) which leads to
+ *
+ * next_freq = C * curr_freq * util_raw / max
+ *
+ * Take C = 1.25 for the frequency tipping point at (util / max) = 0.8.
+ *
+ * The lowest driver-supported frequency which is equal or greater than the raw
+ * next_freq (as calculated above) is returned, subject to policy min/max and
+ * cpufreq driver limitations.
+ */
+static unsigned int get_next_freq(struct sugov_policy *sg_policy,
+ unsigned long util, unsigned long max)
+{
+ struct cpufreq_policy *policy = sg_policy->policy;
+ unsigned int freq = arch_scale_freq_invariant() ?
+ policy->cpuinfo.max_freq : policy->cur;
+
+ freq = (freq + (freq >> 2)) * util / max;
+
+ if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+ return sg_policy->next_freq;
+ sg_policy->cached_raw_freq = freq;
+ return cpufreq_driver_resolve_freq(policy, freq);
+}
+
+static inline bool use_pelt(void)
+{
+#ifdef CONFIG_SCHED_WALT
+ return (!sysctl_sched_use_walt_cpu_util || walt_disabled);
+#else
+ return true;
+#endif
+}
+
+static void sugov_get_util(unsigned long *util, unsigned long *max, u64 time)
+{
+ int cpu = smp_processor_id();
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long max_cap, rt;
+ s64 delta;
+
+ max_cap = arch_scale_cpu_capacity(NULL, cpu);
+
+ sched_avg_update(rq);
+ delta = time - rq->age_stamp;
+ if (unlikely(delta < 0))
+ delta = 0;
+ rt = div64_u64(rq->rt_avg, sched_avg_period() + delta);
+ rt = (rt * max_cap) >> SCHED_CAPACITY_SHIFT;
+
+ *util = boosted_cpu_util(cpu);
+ if (likely(use_pelt()))
+ *util = *util + rt;
+
+ *util = min(*util, max_cap);
+ *max = max_cap;
+}
+
+static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
+ unsigned int flags)
+{
+ if (flags & SCHED_CPUFREQ_IOWAIT) {
+ if (sg_cpu->iowait_boost_pending)
+ return;
+
+ sg_cpu->iowait_boost_pending = true;
+
+ if (sg_cpu->iowait_boost) {
+ sg_cpu->iowait_boost <<= 1;
+ if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
+ sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+ } else {
+ sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
+ }
+ } else if (sg_cpu->iowait_boost) {
+ s64 delta_ns = time - sg_cpu->last_update;
+
+ /* Clear iowait_boost if the CPU apprears to have been idle. */
+ if (delta_ns > TICK_NSEC) {
+ sg_cpu->iowait_boost = 0;
+ sg_cpu->iowait_boost_pending = false;
+ }
+ }
+}
+
+static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
+ unsigned long *max)
+{
+ unsigned int boost_util, boost_max;
+
+ if (!sg_cpu->iowait_boost)
+ return;
+
+ if (sg_cpu->iowait_boost_pending) {
+ sg_cpu->iowait_boost_pending = false;
+ } else {
+ sg_cpu->iowait_boost >>= 1;
+ if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
+ sg_cpu->iowait_boost = 0;
+ return;
+ }
+ }
+
+ boost_util = sg_cpu->iowait_boost;
+ boost_max = sg_cpu->iowait_boost_max;
+
+ if (*util * boost_max < *max * boost_util) {
+ *util = boost_util;
+ *max = boost_max;
+ }
+}
+
+#ifdef CONFIG_NO_HZ_COMMON
+static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
+{
+ unsigned long idle_calls = tick_nohz_get_idle_calls();
+ bool ret = idle_calls == sg_cpu->saved_idle_calls;
+
+ sg_cpu->saved_idle_calls = idle_calls;
+ return ret;
+}
+#else
+static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+#endif /* CONFIG_NO_HZ_COMMON */
+
+static void sugov_update_single(struct update_util_data *hook, u64 time,
+ unsigned int flags)
+{
+ struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+ struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+ struct cpufreq_policy *policy = sg_policy->policy;
+ unsigned long util, max;
+ unsigned int next_f;
+ bool busy;
+
+ sugov_set_iowait_boost(sg_cpu, time, flags);
+ sg_cpu->last_update = time;
+
+ if (!sugov_should_update_freq(sg_policy, time))
+ return;
+
+ busy = sugov_cpu_is_busy(sg_cpu);
+
+ if (flags & SCHED_CPUFREQ_DL) {
+ next_f = policy->cpuinfo.max_freq;
+ } else {
+ sugov_get_util(&util, &max, time);
+ sugov_iowait_boost(sg_cpu, &util, &max);
+ next_f = get_next_freq(sg_policy, util, max);
+ /*
+ * Do not reduce the frequency if the CPU has not been idle
+ * recently, as the reduction is likely to be premature then.
+ */
+ if (busy && next_f < sg_policy->next_freq) {
+ next_f = sg_policy->next_freq;
+
+ /* Reset cached freq as next_freq has changed */
+ sg_policy->cached_raw_freq = 0;
+ }
+ }
+ sugov_update_commit(sg_policy, time, next_f);
+}
+
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
+{
+ struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+ struct cpufreq_policy *policy = sg_policy->policy;
+ unsigned long util = 0, max = 1;
+ unsigned int j;
+
+ for_each_cpu(j, policy->cpus) {
+ struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
+ unsigned long j_util, j_max;
+ s64 delta_ns;
+
+ /*
+ * If the CPU utilization was last updated before the previous
+ * frequency update and the time elapsed between the last update
+ * of the CPU utilization and the last frequency update is long
+ * enough, don't take the CPU into account as it probably is
+ * idle now (and clear iowait_boost for it).
+ */
+ delta_ns = time - j_sg_cpu->last_update;
+ if (delta_ns > TICK_NSEC) {
+ j_sg_cpu->iowait_boost = 0;
+ j_sg_cpu->iowait_boost_pending = false;
+ continue;
+ }
+ if (j_sg_cpu->flags & SCHED_CPUFREQ_DL)
+ return policy->cpuinfo.max_freq;
+
+ j_util = j_sg_cpu->util;
+ j_max = j_sg_cpu->max;
+ if (j_util * max > j_max * util) {
+ util = j_util;
+ max = j_max;
+ }
+
+ sugov_iowait_boost(j_sg_cpu, &util, &max);
+ }
+
+ return get_next_freq(sg_policy, util, max);
+}
+
+static void sugov_update_shared(struct update_util_data *hook, u64 time,
+ unsigned int flags)
+{
+ struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
+ struct sugov_policy *sg_policy = sg_cpu->sg_policy;
+ unsigned long util, max;
+ unsigned int next_f;
+
+ sugov_get_util(&util, &max, time);
+
+ raw_spin_lock(&sg_policy->update_lock);
+
+ sg_cpu->util = util;
+ sg_cpu->max = max;
+ sg_cpu->flags = flags;
+
+ sugov_set_iowait_boost(sg_cpu, time, flags);
+ sg_cpu->last_update = time;
+
+ if (sugov_should_update_freq(sg_policy, time)) {
+ if (flags & SCHED_CPUFREQ_DL)
+ next_f = sg_policy->policy->cpuinfo.max_freq;
+ else
+ next_f = sugov_next_freq_shared(sg_cpu, time);
+
+ sugov_update_commit(sg_policy, time, next_f);
+ }
+
+ raw_spin_unlock(&sg_policy->update_lock);
+}
+
+static void sugov_work(struct kthread_work *work)
+{
+ struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
+
+ mutex_lock(&sg_policy->work_lock);
+ __cpufreq_driver_target(sg_policy->policy, sg_policy->next_freq,
+ CPUFREQ_RELATION_L);
+ mutex_unlock(&sg_policy->work_lock);
+
+ sg_policy->work_in_progress = false;
+}
+
+static void sugov_irq_work(struct irq_work *irq_work)
+{
+ struct sugov_policy *sg_policy;
+
+ sg_policy = container_of(irq_work, struct sugov_policy, irq_work);
+
+ /*
+ * For RT and deadline tasks, the schedutil governor shoots the
+ * frequency to maximum. Special care must be taken to ensure that this
+ * kthread doesn't result in the same behavior.
+ *
+ * This is (mostly) guaranteed by the work_in_progress flag. The flag is
+ * updated only at the end of the sugov_work() function and before that
+ * the schedutil governor rejects all other frequency scaling requests.
+ *
+ * There is a very rare case though, where the RT thread yields right
+ * after the work_in_progress flag is cleared. The effects of that are
+ * neglected for now.
+ */
+ queue_kthread_work(&sg_policy->worker, &sg_policy->work);
+}
+
+/************************** sysfs interface ************************/
+
+static struct sugov_tunables *global_tunables;
+static DEFINE_MUTEX(global_tunables_lock);
+
+static inline struct sugov_tunables *to_sugov_tunables(struct gov_attr_set *attr_set)
+{
+ return container_of(attr_set, struct sugov_tunables, attr_set);
+}
+
+static DEFINE_MUTEX(min_rate_lock);
+
+static void update_min_rate_limit_us(struct sugov_policy *sg_policy)
+{
+ mutex_lock(&min_rate_lock);
+ sg_policy->min_rate_limit_ns = min(sg_policy->up_rate_delay_ns,
+ sg_policy->down_rate_delay_ns);
+ mutex_unlock(&min_rate_lock);
+}
+
+static ssize_t up_rate_limit_us_show(struct gov_attr_set *attr_set, char *buf)
+{
+ struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
+
+ return sprintf(buf, "%u\n", tunables->up_rate_limit_us);
+}
+
+static ssize_t down_rate_limit_us_show(struct gov_attr_set *attr_set, char *buf)
+{
+ struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
+
+ return sprintf(buf, "%u\n", tunables->down_rate_limit_us);
+}
+
+static ssize_t up_rate_limit_us_store(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
+ struct sugov_policy *sg_policy;
+ unsigned int rate_limit_us;
+
+ if (kstrtouint(buf, 10, &rate_limit_us))
+ return -EINVAL;
+
+ tunables->up_rate_limit_us = rate_limit_us;
+
+ list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook) {
+ sg_policy->up_rate_delay_ns = rate_limit_us * NSEC_PER_USEC;
+ update_min_rate_limit_us(sg_policy);
+ }
+
+ return count;
+}
+
+static ssize_t down_rate_limit_us_store(struct gov_attr_set *attr_set,
+ const char *buf, size_t count)
+{
+ struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
+ struct sugov_policy *sg_policy;
+ unsigned int rate_limit_us;
+
+ if (kstrtouint(buf, 10, &rate_limit_us))
+ return -EINVAL;
+
+ tunables->down_rate_limit_us = rate_limit_us;
+
+ list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook) {
+ sg_policy->down_rate_delay_ns = rate_limit_us * NSEC_PER_USEC;
+ update_min_rate_limit_us(sg_policy);
+ }
+
+ return count;
+}
+
+static struct governor_attr up_rate_limit_us = __ATTR_RW(up_rate_limit_us);
+static struct governor_attr down_rate_limit_us = __ATTR_RW(down_rate_limit_us);
+
+static struct attribute *sugov_attributes[] = {
+ &up_rate_limit_us.attr,
+ &down_rate_limit_us.attr,
+ NULL
+};
+
+static struct kobj_type sugov_tunables_ktype = {
+ .default_attrs = sugov_attributes,
+ .sysfs_ops = &governor_sysfs_ops,
+};
+
+/********************** cpufreq governor interface *********************/
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
+static
+#endif
+struct cpufreq_governor cpufreq_gov_schedutil;
+
+static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
+{
+ struct sugov_policy *sg_policy;
+
+ sg_policy = kzalloc(sizeof(*sg_policy), GFP_KERNEL);
+ if (!sg_policy)
+ return NULL;
+
+ sg_policy->policy = policy;
+ raw_spin_lock_init(&sg_policy->update_lock);
+ return sg_policy;
+}
+
+static void sugov_policy_free(struct sugov_policy *sg_policy)
+{
+ kfree(sg_policy);
+}
+
+static int sugov_kthread_create(struct sugov_policy *sg_policy)
+{
+ struct task_struct *thread;
+ struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+ struct cpufreq_policy *policy = sg_policy->policy;
+ int ret;
+
+ /* kthread only required for slow path */
+ if (policy->fast_switch_enabled)
+ return 0;
+
+ init_kthread_work(&sg_policy->work, sugov_work);
+ init_kthread_worker(&sg_policy->worker);
+ thread = kthread_create(kthread_worker_fn, &sg_policy->worker,
+ "sugov:%d",
+ cpumask_first(policy->related_cpus));
+ if (IS_ERR(thread)) {
+ pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread));
+ return PTR_ERR(thread);
+ }
+
+ ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, &param);
+ if (ret) {
+ kthread_stop(thread);
+ pr_warn("%s: failed to set SCHED_FIFO\n", __func__);
+ return ret;
+ }
+
+ sg_policy->thread = thread;
+ kthread_bind_mask(thread, policy->related_cpus);
+ init_irq_work(&sg_policy->irq_work, sugov_irq_work);
+ mutex_init(&sg_policy->work_lock);
+
+ wake_up_process(thread);
+
+ return 0;
+}
+
+static void sugov_kthread_stop(struct sugov_policy *sg_policy)
+{
+ /* kthread only required for slow path */
+ if (sg_policy->policy->fast_switch_enabled)
+ return;
+
+ flush_kthread_worker(&sg_policy->worker);
+ kthread_stop(sg_policy->thread);
+ mutex_destroy(&sg_policy->work_lock);
+}
+
+static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy)
+{
+ struct sugov_tunables *tunables;
+
+ tunables = kzalloc(sizeof(*tunables), GFP_KERNEL);
+ if (tunables) {
+ gov_attr_set_init(&tunables->attr_set, &sg_policy->tunables_hook);
+ if (!have_governor_per_policy())
+ global_tunables = tunables;
+ }
+ return tunables;
+}
+
+static void sugov_tunables_free(struct sugov_tunables *tunables)
+{
+ if (!have_governor_per_policy())
+ global_tunables = NULL;
+
+ kfree(tunables);
+}
+
+static int sugov_init(struct cpufreq_policy *policy)
+{
+ struct sugov_policy *sg_policy;
+ struct sugov_tunables *tunables;
+ int ret = 0;
+
+ /* State should be equivalent to EXIT */
+ if (policy->governor_data)
+ return -EBUSY;
+
+ cpufreq_enable_fast_switch(policy);
+
+ sg_policy = sugov_policy_alloc(policy);
+ if (!sg_policy) {
+ ret = -ENOMEM;
+ goto disable_fast_switch;
+ }
+
+ ret = sugov_kthread_create(sg_policy);
+ if (ret)
+ goto free_sg_policy;
+
+ mutex_lock(&global_tunables_lock);
+
+ if (global_tunables) {
+ if (WARN_ON(have_governor_per_policy())) {
+ ret = -EINVAL;
+ goto stop_kthread;
+ }
+ policy->governor_data = sg_policy;
+ sg_policy->tunables = global_tunables;
+
+ gov_attr_set_get(&global_tunables->attr_set, &sg_policy->tunables_hook);
+ goto out;
+ }
+
+ tunables = sugov_tunables_alloc(sg_policy);
+ if (!tunables) {
+ ret = -ENOMEM;
+ goto stop_kthread;
+ }
+
+ if (policy->up_transition_delay_us && policy->down_transition_delay_us) {
+ tunables->up_rate_limit_us = policy->up_transition_delay_us;
+ tunables->down_rate_limit_us = policy->down_transition_delay_us;
+ } else {
+ unsigned int lat;
+
+ tunables->up_rate_limit_us = LATENCY_MULTIPLIER;
+ tunables->down_rate_limit_us = LATENCY_MULTIPLIER;
+ lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
+ if (lat) {
+ tunables->up_rate_limit_us *= lat;
+ tunables->down_rate_limit_us *= lat;
+ }
+ }
+
+ policy->governor_data = sg_policy;
+ sg_policy->tunables = tunables;
+
+ ret = kobject_init_and_add(&tunables->attr_set.kobj, &sugov_tunables_ktype,
+ get_governor_parent_kobj(policy), "%s",
+ cpufreq_gov_schedutil.name);
+ if (ret)
+ goto fail;
+
+out:
+ mutex_unlock(&global_tunables_lock);
+ return 0;
+
+fail:
+ policy->governor_data = NULL;
+ sugov_tunables_free(tunables);
+
+stop_kthread:
+ sugov_kthread_stop(sg_policy);
+
+free_sg_policy:
+ mutex_unlock(&global_tunables_lock);
+
+ sugov_policy_free(sg_policy);
+
+disable_fast_switch:
+ cpufreq_disable_fast_switch(policy);
+
+ pr_err("initialization failed (error %d)\n", ret);
+ return ret;
+}
+
+static int sugov_exit(struct cpufreq_policy *policy)
+{
+ struct sugov_policy *sg_policy = policy->governor_data;
+ struct sugov_tunables *tunables = sg_policy->tunables;
+ unsigned int count;
+
+ mutex_lock(&global_tunables_lock);
+
+ count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
+ policy->governor_data = NULL;
+ if (!count)
+ sugov_tunables_free(tunables);
+
+ mutex_unlock(&global_tunables_lock);
+
+ sugov_kthread_stop(sg_policy);
+ sugov_policy_free(sg_policy);
+
+ cpufreq_disable_fast_switch(policy);
+ return 0;
+}
+
+static int sugov_start(struct cpufreq_policy *policy)
+{
+ struct sugov_policy *sg_policy = policy->governor_data;
+ unsigned int cpu;
+
+ sg_policy->up_rate_delay_ns =
+ sg_policy->tunables->up_rate_limit_us * NSEC_PER_USEC;
+ sg_policy->down_rate_delay_ns =
+ sg_policy->tunables->down_rate_limit_us * NSEC_PER_USEC;
+ update_min_rate_limit_us(sg_policy);
+ sg_policy->last_freq_update_time = 0;
+ sg_policy->next_freq = UINT_MAX;
+ sg_policy->work_in_progress = false;
+ sg_policy->need_freq_update = false;
+ sg_policy->cached_raw_freq = 0;
+
+ for_each_cpu(cpu, policy->cpus) {
+ struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
+
+ memset(sg_cpu, 0, sizeof(*sg_cpu));
+ sg_cpu->sg_policy = sg_policy;
+ sg_cpu->flags = SCHED_CPUFREQ_DL;
+ sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
+ cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
+ policy_is_shared(policy) ?
+ sugov_update_shared :
+ sugov_update_single);
+ }
+ return 0;
+}
+
+static int sugov_stop(struct cpufreq_policy *policy)
+{
+ struct sugov_policy *sg_policy = policy->governor_data;
+ unsigned int cpu;
+
+ for_each_cpu(cpu, policy->cpus)
+ cpufreq_remove_update_util_hook(cpu);
+
+ synchronize_sched();
+
+ if (!policy->fast_switch_enabled) {
+ irq_work_sync(&sg_policy->irq_work);
+ kthread_cancel_work_sync(&sg_policy->work);
+ }
+ return 0;
+}
+
+static int sugov_limits(struct cpufreq_policy *policy)
+{
+ struct sugov_policy *sg_policy = policy->governor_data;
+
+ if (!policy->fast_switch_enabled) {
+ mutex_lock(&sg_policy->work_lock);
+ cpufreq_policy_apply_limits(policy);
+ mutex_unlock(&sg_policy->work_lock);
+ }
+
+ sg_policy->need_freq_update = true;
+
+ return 0;
+}
+
+static int cpufreq_schedutil_cb(struct cpufreq_policy *policy,
+ unsigned int event)
+{
+ switch(event) {
+ case CPUFREQ_GOV_POLICY_INIT:
+ return sugov_init(policy);
+ case CPUFREQ_GOV_POLICY_EXIT:
+ return sugov_exit(policy);
+ case CPUFREQ_GOV_START:
+ return sugov_start(policy);
+ case CPUFREQ_GOV_STOP:
+ return sugov_stop(policy);
+ case CPUFREQ_GOV_LIMITS:
+ return sugov_limits(policy);
+ default:
+ BUG();
+ }
+}
+
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
+static
+#endif
+struct cpufreq_governor cpufreq_gov_schedutil = {
+ .name = "schedutil",
+ .governor = cpufreq_schedutil_cb,
+ .owner = THIS_MODULE,
+};
+
+static int __init sugov_register(void)
+{
+ return cpufreq_register_governor(&cpufreq_gov_schedutil);
+}
+fs_initcall(sugov_register);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index a1aecbedf5b1..fc2cfd6b2941 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -4,7 +4,9 @@
#include <linux/kernel_stat.h>
#include <linux/static_key.h>
#include <linux/context_tracking.h>
+#include <linux/cpufreq_times.h>
#include "sched.h"
+#include "walt.h"
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -49,6 +51,10 @@ void irqtime_account_irq(struct task_struct *curr)
unsigned long flags;
s64 delta;
int cpu;
+#ifdef CONFIG_SCHED_WALT
+ u64 wallclock;
+ bool account = true;
+#endif
if (!sched_clock_irqtime)
return;
@@ -56,6 +62,9 @@ void irqtime_account_irq(struct task_struct *curr)
local_irq_save(flags);
cpu = smp_processor_id();
+#ifdef CONFIG_SCHED_WALT
+ wallclock = sched_clock_cpu(cpu);
+#endif
delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
__this_cpu_add(irq_start_time, delta);
@@ -70,8 +79,16 @@ void irqtime_account_irq(struct task_struct *curr)
__this_cpu_add(cpu_hardirq_time, delta);
else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
__this_cpu_add(cpu_softirq_time, delta);
+#ifdef CONFIG_SCHED_WALT
+ else
+ account = false;
+#endif
irq_time_write_end();
+#ifdef CONFIG_SCHED_WALT
+ if (account)
+ walt_account_irqtime(cpu, curr, delta, wallclock);
+#endif
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
@@ -149,6 +166,9 @@ void account_user_time(struct task_struct *p, cputime_t cputime,
/* Account for user time used */
acct_account_cputime(p);
+
+ /* Account power usage for user time */
+ cpufreq_acct_update_power(p, cputime);
}
/*
@@ -199,6 +219,9 @@ void __account_system_time(struct task_struct *p, cputime_t cputime,
/* Account for system time used */
acct_account_cputime(p);
+
+ /* Account power usage for system time */
+ cpufreq_acct_update_power(p, cputime);
}
/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8b0a15e285f9..5c6ffddcafcd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -18,6 +18,8 @@
#include <linux/slab.h>
+#include "walt.h"
+
struct dl_bandwidth def_dl_bandwidth;
static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
@@ -43,6 +45,24 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se)
return !RB_EMPTY_NODE(&dl_se->rb_node);
}
+static void add_average_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ u64 se_bw = dl_se->dl_bw;
+
+ dl_rq->avg_bw += se_bw;
+}
+
+static void clear_average_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+ u64 se_bw = dl_se->dl_bw;
+
+ dl_rq->avg_bw -= se_bw;
+ if (dl_rq->avg_bw < 0) {
+ WARN_ON(1);
+ dl_rq->avg_bw = 0;
+ }
+}
+
static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
{
struct sched_dl_entity *dl_se = &p->dl;
@@ -441,13 +461,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
*
* This function returns true if:
*
- * runtime / (deadline - t) > dl_runtime / dl_period ,
+ * runtime / (deadline - t) > dl_runtime / dl_deadline ,
*
* IOW we can't recycle current parameters.
*
- * Notice that the bandwidth check is done against the period. For
+ * Notice that the bandwidth check is done against the deadline. For
* task with deadline equal to period this is the same of using
- * dl_deadline instead of dl_period in the equation above.
+ * dl_period instead of dl_deadline in the equation above.
*/
static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
struct sched_dl_entity *pi_se, u64 t)
@@ -472,7 +492,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
* of anything below microseconds resolution is actually fiction
* (but still we want to give the user that illusion >;).
*/
- left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
right = ((dl_se->deadline - t) >> DL_SCALE) *
(pi_se->dl_runtime >> DL_SCALE);
@@ -480,13 +500,84 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
}
/*
- * When a -deadline entity is queued back on the runqueue, its runtime and
- * deadline might need updating.
+ * Revised wakeup rule [1]: For self-suspending tasks, rather then
+ * re-initializing task's runtime and deadline, the revised wakeup
+ * rule adjusts the task's runtime to avoid the task to overrun its
+ * density.
+ *
+ * Reasoning: a task may overrun the density if:
+ * runtime / (deadline - t) > dl_runtime / dl_deadline
+ *
+ * Therefore, runtime can be adjusted to:
+ * runtime = (dl_runtime / dl_deadline) * (deadline - t)
+ *
+ * In such way that runtime will be equal to the maximum density
+ * the task can use without breaking any rule.
+ *
+ * [1] Luca Abeni, Giuseppe Lipari, and Juri Lelli. 2015. Constant
+ * bandwidth server revisited. SIGBED Rev. 11, 4 (January 2015), 19-24.
+ */
+static void
+update_dl_revised_wakeup(struct sched_dl_entity *dl_se, struct rq *rq)
+{
+ u64 laxity = dl_se->deadline - rq_clock(rq);
+
+ /*
+ * If the task has deadline < period, and the deadline is in the past,
+ * it should already be throttled before this check.
+ *
+ * See update_dl_entity() comments for further details.
+ */
+ WARN_ON(dl_time_before(dl_se->deadline, rq_clock(rq)));
+
+ dl_se->runtime = (dl_se->dl_density * laxity) >> 20;
+}
+
+/*
+ * Regarding the deadline, a task with implicit deadline has a relative
+ * deadline == relative period. A task with constrained deadline has a
+ * relative deadline <= relative period.
+ *
+ * We support constrained deadline tasks. However, there are some restrictions
+ * applied only for tasks which do not have an implicit deadline. See
+ * update_dl_entity() to know more about such restrictions.
+ *
+ * The dl_is_implicit() returns true if the task has an implicit deadline.
+ */
+static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
+{
+ return dl_se->dl_deadline == dl_se->dl_period;
+}
+
+/*
+ * When a deadline entity is placed in the runqueue, its runtime and deadline
+ * might need to be updated. This is done by a CBS wake up rule. There are two
+ * different rules: 1) the original CBS; and 2) the Revisited CBS.
*
- * The policy here is that we update the deadline of the entity only if:
- * - the current deadline is in the past,
- * - using the remaining runtime with the current deadline would make
- * the entity exceed its bandwidth.
+ * When the task is starting a new period, the Original CBS is used. In this
+ * case, the runtime is replenished and a new absolute deadline is set.
+ *
+ * When a task is queued before the begin of the next period, using the
+ * remaining runtime and deadline could make the entity to overflow, see
+ * dl_entity_overflow() to find more about runtime overflow. When such case
+ * is detected, the runtime and deadline need to be updated.
+ *
+ * If the task has an implicit deadline, i.e., deadline == period, the Original
+ * CBS is applied. the runtime is replenished and a new absolute deadline is
+ * set, as in the previous cases.
+ *
+ * However, the Original CBS does not work properly for tasks with
+ * deadline < period, which are said to have a constrained deadline. By
+ * applying the Original CBS, a constrained deadline task would be able to run
+ * runtime/deadline in a period. With deadline < period, the task would
+ * overrun the runtime/period allowed bandwidth, breaking the admission test.
+ *
+ * In order to prevent this misbehave, the Revisited CBS is used for
+ * constrained deadline tasks when a runtime overflow is detected. In the
+ * Revisited CBS, rather than replenishing & setting a new absolute deadline,
+ * the remaining runtime of the task is reduced to avoid runtime overflow.
+ * Please refer to the comments update_dl_revised_wakeup() function to find
+ * more about the Revised CBS rule.
*/
static void update_dl_entity(struct sched_dl_entity *dl_se,
struct sched_dl_entity *pi_se)
@@ -494,6 +585,9 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
+ if (dl_se->dl_new)
+ add_average_bw(dl_se, dl_rq);
+
/*
* The arrival of a new instance needs special treatment, i.e.,
* the actual scheduling parameters have to be "renewed".
@@ -505,15 +599,28 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+
+ if (unlikely(!dl_is_implicit(dl_se) &&
+ !dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+ !dl_se->dl_boosted)){
+ update_dl_revised_wakeup(dl_se, rq);
+ return;
+ }
+
dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
dl_se->runtime = pi_se->dl_runtime;
}
}
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+ return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
/*
* If the entity depleted all its runtime, and if we want it to sleep
* while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
* and try to activate it.
*
* Notice that it is important for the caller to know if the timer
@@ -535,7 +642,7 @@ static int start_dl_timer(struct task_struct *p)
* that it is actually coming from rq->clock and not from
* hrtimer's time base reading.
*/
- act = ns_to_ktime(dl_se->deadline);
+ act = ns_to_ktime(dl_next_period(dl_se));
now = hrtimer_cb_get_time(timer);
delta = ktime_to_ns(now) - rq_clock(rq);
act = ktime_add_ns(act, delta);
@@ -699,6 +806,39 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
timer->function = dl_task_timer;
}
+/*
+ * During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very loaded system, this can cause a domino
+ * effect, making other tasks miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+ if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+ dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+ if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+ return;
+ dl_se->dl_throttled = 1;
+ if (dl_se->runtime > 0)
+ dl_se->runtime = 0;
+ }
+}
+
static
int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
{
@@ -732,6 +872,9 @@ static void update_curr_dl(struct rq *rq)
if (unlikely((s64)delta_exec <= 0))
return;
+ /* kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_DL);
+
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
@@ -741,8 +884,6 @@ static void update_curr_dl(struct rq *rq)
curr->se.exec_start = rq_clock_task(rq);
cpuacct_charge(curr, delta_exec);
- sched_rt_avg_update(rq, delta_exec);
-
dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
if (dl_runtime_exceeded(dl_se)) {
dl_se->dl_throttled = 1;
@@ -860,6 +1001,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
WARN_ON(!dl_prio(prio));
dl_rq->dl_nr_running++;
add_nr_running(rq_of_dl_rq(dl_rq), 1);
+ walt_inc_cumulative_runnable_avg(rq_of_dl_rq(dl_rq), dl_task_of(dl_se));
inc_dl_deadline(dl_rq, deadline);
inc_dl_migration(dl_se, dl_rq);
@@ -874,6 +1016,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
WARN_ON(!dl_rq->dl_nr_running);
dl_rq->dl_nr_running--;
sub_nr_running(rq_of_dl_rq(dl_rq), 1);
+ walt_dec_cumulative_runnable_avg(rq_of_dl_rq(dl_rq), dl_task_of(dl_se));
dec_dl_deadline(dl_rq, dl_se->deadline);
dec_dl_migration(dl_se, dl_rq);
@@ -979,6 +1122,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
}
/*
+ * Check if a constrained deadline task was activated
+ * after the deadline but before the next period.
+ * If that is the case, the task will be throttled and
+ * the replenishment timer will be set to the next period.
+ */
+ if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl))
+ dl_check_constrained_dl(&p->dl);
+
+ /*
* If p is throttled, we do nothing. In fact, if it exhausted
* its budget it needs a replenishment and, since it now is on
* its rq, the bandwidth timer callback (which clearly has not
@@ -1044,7 +1196,8 @@ static void yield_task_dl(struct rq *rq)
static int find_later_rq(struct task_struct *task);
static int
-select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags,
+ int sibling_count_hint)
{
struct task_struct *curr;
struct rq *rq;
@@ -1241,6 +1394,8 @@ static void task_fork_dl(struct task_struct *p)
static void task_dead_dl(struct task_struct *p)
{
struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+ struct dl_rq *dl_rq = dl_rq_of_se(&p->dl);
+ struct rq *rq = rq_of_dl_rq(dl_rq);
/*
* Since we are TASK_DEAD we won't slip out of the domain!
@@ -1249,6 +1404,8 @@ static void task_dead_dl(struct task_struct *p)
/* XXX we should retain the bw until 0-lag */
dl_b->total_bw -= p->dl.dl_bw;
raw_spin_unlock_irq(&dl_b->lock);
+
+ clear_average_bw(&p->dl, &rq->dl);
}
static void set_curr_task_dl(struct rq *rq)
@@ -1556,7 +1713,11 @@ retry:
}
deactivate_task(rq, next_task, 0);
+ clear_average_bw(&next_task->dl, &rq->dl);
+ next_task->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(next_task, later_rq->cpu);
+ next_task->on_rq = TASK_ON_RQ_QUEUED;
+ add_average_bw(&next_task->dl, &later_rq->dl);
activate_task(later_rq, next_task, 0);
ret = 1;
@@ -1644,7 +1805,11 @@ static void pull_dl_task(struct rq *this_rq)
resched = true;
deactivate_task(src_rq, p, 0);
+ clear_average_bw(&p->dl, &src_rq->dl);
+ p->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(p, this_cpu);
+ p->on_rq = TASK_ON_RQ_QUEUED;
+ add_average_bw(&p->dl, &this_rq->dl);
activate_task(this_rq, p, 0);
dmin = p->dl.deadline;
@@ -1750,6 +1915,8 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
if (!start_dl_timer(p))
__dl_clear_params(p);
+ clear_average_bw(&p->dl, &rq->dl);
+
/*
* Since this might be the only -deadline task on the rq,
* this is the right place to try to pull some other one
@@ -1771,12 +1938,11 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
#ifdef CONFIG_SMP
if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
queue_push_tasks(rq);
-#else
+#endif
if (dl_task(rq->curr))
check_preempt_curr_dl(rq, p, 0);
else
resched_curr(rq);
-#endif
}
}
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 641511771ae6..7f7116622631 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -597,6 +597,32 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
P(se.statistics.nr_wakeups_affine_attempts);
P(se.statistics.nr_wakeups_passive);
P(se.statistics.nr_wakeups_idle);
+ /* eas */
+ /* select_idle_sibling() */
+ P(se.statistics.nr_wakeups_sis_attempts);
+ P(se.statistics.nr_wakeups_sis_idle);
+ P(se.statistics.nr_wakeups_sis_cache_affine);
+ P(se.statistics.nr_wakeups_sis_suff_cap);
+ P(se.statistics.nr_wakeups_sis_idle_cpu);
+ P(se.statistics.nr_wakeups_sis_count);
+ /* select_energy_cpu_brute() */
+ P(se.statistics.nr_wakeups_secb_attempts);
+ P(se.statistics.nr_wakeups_secb_sync);
+ P(se.statistics.nr_wakeups_secb_idle_bt);
+ P(se.statistics.nr_wakeups_secb_insuff_cap);
+ P(se.statistics.nr_wakeups_secb_no_nrg_sav);
+ P(se.statistics.nr_wakeups_secb_nrg_sav);
+ P(se.statistics.nr_wakeups_secb_count);
+ /* find_best_target() */
+ P(se.statistics.nr_wakeups_fbt_attempts);
+ P(se.statistics.nr_wakeups_fbt_no_cpu);
+ P(se.statistics.nr_wakeups_fbt_no_sd);
+ P(se.statistics.nr_wakeups_fbt_pref_idle);
+ P(se.statistics.nr_wakeups_fbt_count);
+ /* cas */
+ /* select_task_rq_fair() */
+ P(se.statistics.nr_wakeups_cas_attempts);
+ P(se.statistics.nr_wakeups_cas_count);
{
u64 avg_atom, avg_per_cpu;
diff --git a/kernel/sched/energy.c b/kernel/sched/energy.c
new file mode 100644
index 000000000000..b0656b7a93e3
--- /dev/null
+++ b/kernel/sched/energy.c
@@ -0,0 +1,124 @@
+/*
+ * Obtain energy cost data from DT and populate relevant scheduler data
+ * structures.
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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, see <http://www.gnu.org/licenses/>.
+ */
+#define pr_fmt(fmt) "sched-energy: " fmt
+
+#define DEBUG
+
+#include <linux/gfp.h>
+#include <linux/of.h>
+#include <linux/printk.h>
+#include <linux/sched.h>
+#include <linux/sched_energy.h>
+#include <linux/stddef.h>
+
+struct sched_group_energy *sge_array[NR_CPUS][NR_SD_LEVELS];
+
+static void free_resources(void)
+{
+ int cpu, sd_level;
+ struct sched_group_energy *sge;
+
+ for_each_possible_cpu(cpu) {
+ for_each_possible_sd_level(sd_level) {
+ sge = sge_array[cpu][sd_level];
+ if (sge) {
+ kfree(sge->cap_states);
+ kfree(sge->idle_states);
+ kfree(sge);
+ }
+ }
+ }
+}
+
+void init_sched_energy_costs(void)
+{
+ struct device_node *cn, *cp;
+ struct capacity_state *cap_states;
+ struct idle_state *idle_states;
+ struct sched_group_energy *sge;
+ const struct property *prop;
+ int sd_level, i, nstates, cpu;
+ const __be32 *val;
+
+ for_each_possible_cpu(cpu) {
+ cn = of_get_cpu_node(cpu, NULL);
+ if (!cn) {
+ pr_warn("CPU device node missing for CPU %d\n", cpu);
+ return;
+ }
+
+ if (!of_find_property(cn, "sched-energy-costs", NULL)) {
+ pr_warn("CPU device node has no sched-energy-costs\n");
+ return;
+ }
+
+ for_each_possible_sd_level(sd_level) {
+ cp = of_parse_phandle(cn, "sched-energy-costs", sd_level);
+ if (!cp)
+ break;
+
+ prop = of_find_property(cp, "busy-cost-data", NULL);
+ if (!prop || !prop->value) {
+ pr_warn("No busy-cost data, skipping sched_energy init\n");
+ goto out;
+ }
+
+ sge = kcalloc(1, sizeof(struct sched_group_energy),
+ GFP_NOWAIT);
+
+ nstates = (prop->length / sizeof(u32)) / 2;
+ cap_states = kcalloc(nstates,
+ sizeof(struct capacity_state),
+ GFP_NOWAIT);
+
+ for (i = 0, val = prop->value; i < nstates; i++) {
+ cap_states[i].cap = be32_to_cpup(val++);
+ cap_states[i].power = be32_to_cpup(val++);
+ }
+
+ sge->nr_cap_states = nstates;
+ sge->cap_states = cap_states;
+
+ prop = of_find_property(cp, "idle-cost-data", NULL);
+ if (!prop || !prop->value) {
+ pr_warn("No idle-cost data, skipping sched_energy init\n");
+ goto out;
+ }
+
+ nstates = (prop->length / sizeof(u32));
+ idle_states = kcalloc(nstates,
+ sizeof(struct idle_state),
+ GFP_NOWAIT);
+
+ for (i = 0, val = prop->value; i < nstates; i++)
+ idle_states[i].power = be32_to_cpup(val++);
+
+ sge->nr_idle_states = nstates;
+ sge->idle_states = idle_states;
+
+ sge_array[cpu][sd_level] = sge;
+ }
+ }
+
+ pr_info("Sched-energy-costs installed from DT\n");
+ return;
+
+out:
+ free_resources();
+}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8f258f437ac2..cf5916ea2ae1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -30,10 +30,13 @@
#include <linux/mempolicy.h>
#include <linux/migrate.h>
#include <linux/task_work.h>
+#include <linux/module.h>
#include <trace/events/sched.h>
#include "sched.h"
+#include "tune.h"
+#include "walt.h"
/*
* Targeted preemption latency for CPU-bound tasks:
@@ -50,6 +53,15 @@
unsigned int sysctl_sched_latency = 6000000ULL;
unsigned int normalized_sysctl_sched_latency = 6000000ULL;
+unsigned int sysctl_sched_sync_hint_enable = 1;
+unsigned int sysctl_sched_cstate_aware = 1;
+
+#ifdef CONFIG_SCHED_WALT
+unsigned int sysctl_sched_use_walt_cpu_util = 1;
+unsigned int sysctl_sched_use_walt_task_util = 1;
+__read_mostly unsigned int sysctl_sched_walt_cpu_high_irqload =
+ (10 * NSEC_PER_MSEC);
+#endif
/*
* The initial- and re-scaling of tunables is configurable
* (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
@@ -114,6 +126,12 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
#endif
+/*
+ * The margin used when comparing utilization with CPU capacity:
+ * util * margin < capacity * 1024
+ */
+unsigned int capacity_margin = 1280; /* ~20% */
+
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
@@ -286,19 +304,59 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
if (!cfs_rq->on_list) {
+ struct rq *rq = rq_of(cfs_rq);
+ int cpu = cpu_of(rq);
/*
* Ensure we either appear before our parent (if already
* enqueued) or force our parent to appear after us when it is
- * enqueued. The fact that we always enqueue bottom-up
- * reduces this to two cases.
+ * enqueued. The fact that we always enqueue bottom-up
+ * reduces this to two cases and a special case for the root
+ * cfs_rq. Furthermore, it also means that we will always reset
+ * tmp_alone_branch either when the branch is connected
+ * to a tree or when we reach the beg of the tree
*/
if (cfs_rq->tg->parent &&
- cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
- list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
- &rq_of(cfs_rq)->leaf_cfs_rq_list);
- } else {
+ cfs_rq->tg->parent->cfs_rq[cpu]->on_list) {
+ /*
+ * If parent is already on the list, we add the child
+ * just before. Thanks to circular linked property of
+ * the list, this means to put the child at the tail
+ * of the list that starts by parent.
+ */
list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
- &rq_of(cfs_rq)->leaf_cfs_rq_list);
+ &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list));
+ /*
+ * The branch is now connected to its tree so we can
+ * reset tmp_alone_branch to the beginning of the
+ * list.
+ */
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+ } else if (!cfs_rq->tg->parent) {
+ /*
+ * cfs rq without parent should be put
+ * at the tail of the list.
+ */
+ list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
+ &rq->leaf_cfs_rq_list);
+ /*
+ * We have reach the beg of a tree so we can reset
+ * tmp_alone_branch to the beginning of the list.
+ */
+ rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
+ } else {
+ /*
+ * The parent has not already been added so we want to
+ * make sure that it will be put after us.
+ * tmp_alone_branch points to the beg of the branch
+ * where we will add parent.
+ */
+ list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
+ rq->tmp_alone_branch);
+ /*
+ * update tmp_alone_branch to points to the new beg
+ * of the branch
+ */
+ rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
}
cfs_rq->on_list = 1;
@@ -656,7 +714,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
#ifdef CONFIG_SMP
-static int select_idle_sibling(struct task_struct *p, int cpu);
+static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
static unsigned long task_h_load(struct task_struct *p);
/*
@@ -680,18 +738,115 @@ void init_entity_runnable_average(struct sched_entity *se)
* will definitely be update (after enqueue).
*/
sa->period_contrib = 1023;
- sa->load_avg = scale_load_down(se->load.weight);
+ /*
+ * Tasks are intialized with full load to be seen as heavy tasks until
+ * they get a chance to stabilize to their real load level.
+ * Group entities are intialized with zero load to reflect the fact that
+ * nothing has been attached to the task group yet.
+ */
+ if (entity_is_task(se))
+ sa->load_avg = scale_load_down(se->load.weight);
sa->load_sum = sa->load_avg * LOAD_AVG_MAX;
- sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
- sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+ /*
+ * In previous Android versions, we used to have:
+ * sa->util_avg = scale_load_down(SCHED_LOAD_SCALE);
+ * sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+ * However, that functionality has been moved to enqueue.
+ * It is unclear if we should restore this in enqueue.
+ */
+ /*
+ * At this point, util_avg won't be used in select_task_rq_fair anyway
+ */
+ sa->util_avg = 0;
+ sa->util_sum = 0;
/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
}
-#else
+static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
+static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq);
+static void attach_entity_cfs_rq(struct sched_entity *se);
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
+/*
+ * With new tasks being created, their initial util_avgs are extrapolated
+ * based on the cfs_rq's current util_avg:
+ *
+ * util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight
+ *
+ * However, in many cases, the above util_avg does not give a desired
+ * value. Moreover, the sum of the util_avgs may be divergent, such
+ * as when the series is a harmonic series.
+ *
+ * To solve this problem, we also cap the util_avg of successive tasks to
+ * only 1/2 of the left utilization budget:
+ *
+ * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ *
+ * where n denotes the nth task.
+ *
+ * For example, a simplest series from the beginning would be like:
+ *
+ * task util_avg: 512, 256, 128, 64, 32, 16, 8, ...
+ * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
+ *
+ * Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap)
+ * if util_avg > util_avg_cap.
+ */
+void post_init_entity_util_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ struct sched_avg *sa = &se->avg;
+ long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+
+ if (cap > 0) {
+ if (cfs_rq->avg.util_avg != 0) {
+ sa->util_avg = cfs_rq->avg.util_avg * se->load.weight;
+ sa->util_avg /= (cfs_rq->avg.load_avg + 1);
+
+ if (sa->util_avg > cap)
+ sa->util_avg = cap;
+ } else {
+ sa->util_avg = cap;
+ }
+ /*
+ * If we wish to restore tuning via setting initial util,
+ * this is where we should do it.
+ */
+ sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
+ }
+
+ if (entity_is_task(se)) {
+ struct task_struct *p = task_of(se);
+ if (p->sched_class != &fair_sched_class) {
+ /*
+ * For !fair tasks do:
+ *
+ update_cfs_rq_load_avg(now, cfs_rq, false);
+ attach_entity_load_avg(cfs_rq, se);
+ switched_from_fair(rq, p);
+ *
+ * such that the next switched_to_fair() has the
+ * expected state.
+ */
+ se->avg.last_update_time = cfs_rq_clock_task(cfs_rq);
+ return;
+ }
+ }
+
+ attach_entity_cfs_rq(se);
+}
+
+#else /* !CONFIG_SMP */
void init_entity_runnable_average(struct sched_entity *se)
{
}
-#endif
+void post_init_entity_util_avg(struct sched_entity *se)
+{
+}
+static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
+{
+}
+#endif /* CONFIG_SMP */
/*
* Update the current task's runtime statistics.
@@ -1388,7 +1543,8 @@ balance:
* Call select_idle_sibling to maybe find a better one.
*/
if (!cur)
- env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
+ env->dst_cpu = select_idle_sibling(env->p, env->src_cpu,
+ env->dst_cpu);
assign:
assigned = true;
@@ -1722,6 +1878,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
if (p->last_task_numa_placement) {
delta = runtime - p->last_sum_exec_runtime;
*period = now - p->last_task_numa_placement;
+
+ /* Avoid time going backwards, prevent potential divide error: */
+ if (unlikely((s64)*period < 0))
+ *period = 0;
} else {
delta = p->se.avg.load_sum / p->se.load.weight;
*period = LOAD_AVG_MAX;
@@ -2223,7 +2383,8 @@ void task_numa_work(struct callback_head *work)
return;
- down_read(&mm->mmap_sem);
+ if (!down_read_trylock(&mm->mmap_sem))
+ return;
vma = find_vma(mm, start);
if (!vma) {
reset_ptenuma_scan(p);
@@ -2373,28 +2534,22 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
#ifdef CONFIG_FAIR_GROUP_SCHED
# ifdef CONFIG_SMP
-static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
- long tg_weight;
+ long tg_weight, load, shares;
/*
- * Use this CPU's real-time load instead of the last load contribution
- * as the updating of the contribution is delayed, and we will use the
- * the real-time load to calc the share. See update_tg_load_avg().
+ * This really should be: cfs_rq->avg.load_avg, but instead we use
+ * cfs_rq->load.weight, which is its upper bound. This helps ramp up
+ * the shares for small weight interactive tasks.
*/
- tg_weight = atomic_long_read(&tg->load_avg);
- tg_weight -= cfs_rq->tg_load_avg_contrib;
- tg_weight += cfs_rq->load.weight;
-
- return tg_weight;
-}
+ load = scale_load_down(cfs_rq->load.weight);
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
-{
- long tg_weight, load, shares;
+ tg_weight = atomic_long_read(&tg->load_avg);
- tg_weight = calc_tg_weight(tg, cfs_rq);
- load = cfs_rq->load.weight;
+ /* Ensure tg_weight >= load */
+ tg_weight -= cfs_rq->tg_load_avg_contrib;
+ tg_weight += load;
shares = (tg->shares * load);
if (tg_weight)
@@ -2413,6 +2568,7 @@ static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
return tg->shares;
}
# endif /* CONFIG_SMP */
+
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
unsigned long weight)
{
@@ -2431,16 +2587,20 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
-static void update_cfs_shares(struct cfs_rq *cfs_rq)
+static void update_cfs_shares(struct sched_entity *se)
{
+ struct cfs_rq *cfs_rq = group_cfs_rq(se);
struct task_group *tg;
- struct sched_entity *se;
long shares;
- tg = cfs_rq->tg;
- se = tg->se[cpu_of(rq_of(cfs_rq))];
- if (!se || throttled_hierarchy(cfs_rq))
+ if (!cfs_rq)
+ return;
+
+ if (throttled_hierarchy(cfs_rq))
return;
+
+ tg = cfs_rq->tg;
+
#ifndef CONFIG_SMP
if (likely(se->load.weight == tg->shares))
return;
@@ -2449,8 +2609,9 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq)
reweight_entity(cfs_rq_of(se), se, shares);
}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
+static inline void update_cfs_shares(struct sched_entity *se)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -2600,6 +2761,7 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
scale_freq = arch_scale_freq_capacity(NULL, cpu);
scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+ trace_sched_contrib_scale_f(cpu, scale_freq, scale_cpu);
/* delta_w is the amount already accumulated against our next period */
delta_w = sa->period_contrib;
@@ -2675,25 +2837,262 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
return decayed;
}
-#ifdef CONFIG_FAIR_GROUP_SCHED
/*
- * Updating tg's load_avg is necessary before update_cfs_share (which is done)
- * and effective_load (which is not done because it is too costly).
+ * Signed add and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+#define add_positive(_ptr, _val) do { \
+ typeof(_ptr) ptr = (_ptr); \
+ typeof(_val) val = (_val); \
+ typeof(*ptr) res, var = READ_ONCE(*ptr); \
+ \
+ res = var + val; \
+ \
+ if (val < 0 && res > var) \
+ res = 0; \
+ \
+ WRITE_ONCE(*ptr, res); \
+} while (0)
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/**
+ * update_tg_load_avg - update the tg's load avg
+ * @cfs_rq: the cfs_rq whose avg changed
+ * @force: update regardless of how small the difference
+ *
+ * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load.
+ * However, because tg->load_avg is a global value there are performance
+ * considerations.
+ *
+ * In order to avoid having to look at the other cfs_rq's, we use a
+ * differential update where we store the last value we propagated. This in
+ * turn allows skipping updates if the differential is 'small'.
+ *
+ * Updating tg's load_avg is necessary before update_cfs_share() (which is
+ * done) and effective_load() (which is not done because it is too costly).
*/
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
{
long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib;
+ /*
+ * No need to update load_avg for root_task_group as it is not used.
+ */
+ if (cfs_rq->tg == &root_task_group)
+ return;
+
if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) {
atomic_long_add(delta, &cfs_rq->tg->load_avg);
cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg;
}
}
+/*
+ * Called within set_task_rq() right before setting a task's cpu. The
+ * caller only guarantees p->pi_lock is held; no other assumptions,
+ * including the state of rq->lock, should be made.
+ */
+void set_task_rq_fair(struct sched_entity *se,
+ struct cfs_rq *prev, struct cfs_rq *next)
+{
+ if (!sched_feat(ATTACH_AGE_LOAD))
+ return;
+
+ /*
+ * We are supposed to update the task to "current" time, then its up to
+ * date and ready to go to new CPU/cfs_rq. But we have difficulty in
+ * getting what current time is, so simply throw away the out-of-date
+ * time. This will result in the wakee task is less decayed, but giving
+ * the wakee more load sounds not bad.
+ */
+ if (se->avg.last_update_time && prev) {
+ u64 p_last_update_time;
+ u64 n_last_update_time;
+
+#ifndef CONFIG_64BIT
+ u64 p_last_update_time_copy;
+ u64 n_last_update_time_copy;
+
+ do {
+ p_last_update_time_copy = prev->load_last_update_time_copy;
+ n_last_update_time_copy = next->load_last_update_time_copy;
+
+ smp_rmb();
+
+ p_last_update_time = prev->avg.last_update_time;
+ n_last_update_time = next->avg.last_update_time;
+
+ } while (p_last_update_time != p_last_update_time_copy ||
+ n_last_update_time != n_last_update_time_copy);
+#else
+ p_last_update_time = prev->avg.last_update_time;
+ n_last_update_time = next->avg.last_update_time;
+#endif
+ __update_load_avg(p_last_update_time, cpu_of(rq_of(prev)),
+ &se->avg, 0, 0, NULL);
+ se->avg.last_update_time = n_last_update_time;
+ }
+}
+
+/* Take into account change of utilization of a child task group */
+static inline void
+update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+ long delta = gcfs_rq->avg.util_avg - se->avg.util_avg;
+
+ /* Nothing to update */
+ if (!delta)
+ return;
+
+ /* Set new sched_entity's utilization */
+ se->avg.util_avg = gcfs_rq->avg.util_avg;
+ se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX;
+
+ /* Update parent cfs_rq utilization */
+ add_positive(&cfs_rq->avg.util_avg, delta);
+ cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX;
+}
+
+/* Take into account change of load of a child task group */
+static inline void
+update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+ long delta, load = gcfs_rq->avg.load_avg;
+
+ /*
+ * If the load of group cfs_rq is null, the load of the
+ * sched_entity will also be null so we can skip the formula
+ */
+ if (load) {
+ long tg_load;
+
+ /* Get tg's load and ensure tg_load > 0 */
+ tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1;
+
+ /* Ensure tg_load >= load and updated with current load*/
+ tg_load -= gcfs_rq->tg_load_avg_contrib;
+ tg_load += load;
+
+ /*
+ * We need to compute a correction term in the case that the
+ * task group is consuming more CPU than a task of equal
+ * weight. A task with a weight equals to tg->shares will have
+ * a load less or equal to scale_load_down(tg->shares).
+ * Similarly, the sched_entities that represent the task group
+ * at parent level, can't have a load higher than
+ * scale_load_down(tg->shares). And the Sum of sched_entities'
+ * load must be <= scale_load_down(tg->shares).
+ */
+ if (tg_load > scale_load_down(gcfs_rq->tg->shares)) {
+ /* scale gcfs_rq's load into tg's shares*/
+ load *= scale_load_down(gcfs_rq->tg->shares);
+ load /= tg_load;
+ }
+ }
+
+ delta = load - se->avg.load_avg;
+
+ /* Nothing to update */
+ if (!delta)
+ return;
+
+ /* Set new sched_entity's load */
+ se->avg.load_avg = load;
+ se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX;
+
+ /* Update parent cfs_rq load */
+ add_positive(&cfs_rq->avg.load_avg, delta);
+ cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX;
+
+ /*
+ * If the sched_entity is already enqueued, we also have to update the
+ * runnable load avg.
+ */
+ if (se->on_rq) {
+ /* Update parent cfs_rq runnable_load_avg */
+ add_positive(&cfs_rq->runnable_load_avg, delta);
+ cfs_rq->runnable_load_sum = cfs_rq->runnable_load_avg * LOAD_AVG_MAX;
+ }
+}
+
+static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq)
+{
+ cfs_rq->propagate_avg = 1;
+}
+
+static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = group_cfs_rq(se);
+
+ if (!cfs_rq->propagate_avg)
+ return 0;
+
+ cfs_rq->propagate_avg = 0;
+ return 1;
+}
+
+/* Update task and its cfs_rq load average */
+static inline int propagate_entity_load_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq;
+
+ if (entity_is_task(se))
+ return 0;
+
+ if (!test_and_clear_tg_cfs_propagate(se))
+ return 0;
+
+ cfs_rq = cfs_rq_of(se);
+
+ set_tg_cfs_propagate(cfs_rq);
+
+ update_tg_cfs_util(cfs_rq, se);
+ update_tg_cfs_load(cfs_rq, se);
+
+ return 1;
+}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
+
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
+
+static inline int propagate_entity_load_avg(struct sched_entity *se)
+{
+ return 0;
+}
+
+static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {}
+
#endif /* CONFIG_FAIR_GROUP_SCHED */
+static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
+{
+ if (&this_rq()->cfs == cfs_rq) {
+ /*
+ * There are a few boundary cases this might miss but it should
+ * get called often enough that that should (hopefully) not be
+ * a real problem -- added to that it only calls on the local
+ * CPU, so if we enqueue remotely we'll miss an update, but
+ * the next tick/schedule should update.
+ *
+ * It will not get called when we go idle, because the idle
+ * thread is a different class (!fair), nor will the utilization
+ * number include things like RT tasks.
+ *
+ * As is, the util number is not freq-invariant (we'd have to
+ * implement arch_scale_freq_capacity() for that).
+ *
+ * See cpu_util().
+ */
+ cpufreq_update_util(rq_of(cfs_rq), 0);
+ }
+}
+
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
/*
@@ -2713,23 +3112,43 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
WRITE_ONCE(*ptr, res); \
} while (0)
-/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
-static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+/**
+ * update_cfs_rq_load_avg - update the cfs_rq's load/util averages
+ * @now: current time, as per cfs_rq_clock_task()
+ * @cfs_rq: cfs_rq to update
+ * @update_freq: should we call cfs_rq_util_change() or will the call do so
+ *
+ * The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
+ * avg. The immediate corollary is that all (fair) tasks must be attached, see
+ * post_init_entity_util_avg().
+ *
+ * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example.
+ *
+ * Returns true if the load decayed or we removed load.
+ *
+ * Since both these conditions indicate a changed cfs_rq->avg.load we should
+ * call update_tg_load_avg() when this function returns true.
+ */
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
{
struct sched_avg *sa = &cfs_rq->avg;
- int decayed, removed = 0;
+ int decayed, removed = 0, removed_util = 0;
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
sub_positive(&sa->load_avg, r);
sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
removed = 1;
+ set_tg_cfs_propagate(cfs_rq);
}
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
sub_positive(&sa->util_avg, r);
sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
+ removed_util = 1;
+ set_tg_cfs_propagate(cfs_rq);
}
decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
@@ -2740,65 +3159,93 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
cfs_rq->load_last_update_time_copy = sa->last_update_time;
#endif
+ /* Trace CPU load, unless cfs_rq belongs to a non-root task_group */
+ if (cfs_rq == &rq_of(cfs_rq)->cfs)
+ trace_sched_load_avg_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq);
+
+ if (update_freq && (decayed || removed_util))
+ cfs_rq_util_change(cfs_rq);
+
return decayed || removed;
}
+/*
+ * Optional action to be done while updating the load average
+ */
+#define UPDATE_TG 0x1
+#define SKIP_AGE_LOAD 0x2
+
/* Update task and its cfs_rq load average */
-static inline void update_load_avg(struct sched_entity *se, int update_tg)
+static inline void update_load_avg(struct sched_entity *se, int flags)
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
u64 now = cfs_rq_clock_task(cfs_rq);
int cpu = cpu_of(rq_of(cfs_rq));
+ int decayed;
+ void *ptr = NULL;
/*
* Track task load average for carrying it to new CPU after migrated, and
* track group sched_entity load average for task_h_load calc in migration
*/
- __update_load_avg(now, cpu, &se->avg,
+ if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) {
+ __update_load_avg(now, cpu, &se->avg,
se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
+ }
+
+ decayed = update_cfs_rq_load_avg(now, cfs_rq, true);
+ decayed |= propagate_entity_load_avg(se);
- if (update_cfs_rq_load_avg(now, cfs_rq) && update_tg)
+ if (decayed && (flags & UPDATE_TG))
update_tg_load_avg(cfs_rq, 0);
+
+ if (entity_is_task(se)) {
+#ifdef CONFIG_SCHED_WALT
+ ptr = (void *)&(task_of(se)->ravg);
+#endif
+ trace_sched_load_avg_task(task_of(se), &se->avg, ptr);
+ }
}
+/**
+ * attach_entity_load_avg - attach this entity to its cfs_rq load avg
+ * @cfs_rq: cfs_rq to attach to
+ * @se: sched_entity to attach
+ *
+ * Must call update_cfs_rq_load_avg() before this, since we rely on
+ * cfs_rq->avg.last_update_time being current.
+ */
static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (!sched_feat(ATTACH_AGE_LOAD))
- goto skip_aging;
-
- /*
- * If we got migrated (either between CPUs or between cgroups) we'll
- * have aged the average right before clearing @last_update_time.
- */
- if (se->avg.last_update_time) {
- __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
- &se->avg, 0, 0, NULL);
-
- /*
- * XXX: we could have just aged the entire load away if we've been
- * absent from the fair class for too long.
- */
- }
-
-skip_aging:
se->avg.last_update_time = cfs_rq->avg.last_update_time;
cfs_rq->avg.load_avg += se->avg.load_avg;
cfs_rq->avg.load_sum += se->avg.load_sum;
cfs_rq->avg.util_avg += se->avg.util_avg;
cfs_rq->avg.util_sum += se->avg.util_sum;
+ set_tg_cfs_propagate(cfs_rq);
+
+ cfs_rq_util_change(cfs_rq);
}
+/**
+ * detach_entity_load_avg - detach this entity from its cfs_rq load avg
+ * @cfs_rq: cfs_rq to detach from
+ * @se: sched_entity to detach
+ *
+ * Must call update_cfs_rq_load_avg() before this, since we rely on
+ * cfs_rq->avg.last_update_time being current.
+ */
static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
- &se->avg, se->on_rq * scale_load_down(se->load.weight),
- cfs_rq->curr == se, NULL);
sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
+ set_tg_cfs_propagate(cfs_rq);
+
+ cfs_rq_util_change(cfs_rq);
}
/* Add the load generated by se into cfs_rq's load average */
@@ -2806,62 +3253,79 @@ static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct sched_avg *sa = &se->avg;
- u64 now = cfs_rq_clock_task(cfs_rq);
- int migrated, decayed;
-
- migrated = !sa->last_update_time;
- if (!migrated) {
- __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
- se->on_rq * scale_load_down(se->load.weight),
- cfs_rq->curr == se, NULL);
- }
-
- decayed = update_cfs_rq_load_avg(now, cfs_rq);
cfs_rq->runnable_load_avg += sa->load_avg;
cfs_rq->runnable_load_sum += sa->load_sum;
- if (migrated)
+ if (!sa->last_update_time) {
attach_entity_load_avg(cfs_rq, se);
-
- if (decayed || migrated)
update_tg_load_avg(cfs_rq, 0);
+ }
}
/* Remove the runnable load generated by se from cfs_rq's runnable load average */
static inline void
dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- update_load_avg(se, 1);
-
cfs_rq->runnable_load_avg =
max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0);
cfs_rq->runnable_load_sum =
max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0);
}
-/*
- * Task first catches up with cfs_rq, and then subtract
- * itself from the cfs_rq (task must be off the queue now).
- */
-void remove_entity_load_avg(struct sched_entity *se)
-{
- struct cfs_rq *cfs_rq = cfs_rq_of(se);
- u64 last_update_time;
-
#ifndef CONFIG_64BIT
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
u64 last_update_time_copy;
+ u64 last_update_time;
do {
last_update_time_copy = cfs_rq->load_last_update_time_copy;
smp_rmb();
last_update_time = cfs_rq->avg.last_update_time;
} while (last_update_time != last_update_time_copy);
+
+ return last_update_time;
+}
#else
- last_update_time = cfs_rq->avg.last_update_time;
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
+ return cfs_rq->avg.last_update_time;
+}
#endif
+/*
+ * Synchronize entity load avg of dequeued entity without locking
+ * the previous rq.
+ */
+void sync_entity_load_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ u64 last_update_time;
+
+ last_update_time = cfs_rq_last_update_time(cfs_rq);
__update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+}
+
+/*
+ * Task first catches up with cfs_rq, and then subtract
+ * itself from the cfs_rq (task must be off the queue now).
+ */
+void remove_entity_load_avg(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /*
+ * tasks cannot exit without having gone through wake_up_new_task() ->
+ * post_init_entity_util_avg() which will have added things to the
+ * cfs_rq, so we can remove unconditionally.
+ *
+ * Similarly for groups, they will have passed through
+ * post_init_entity_util_avg() before unregister_sched_fair_group()
+ * calls this.
+ */
+
+ sync_entity_load_avg(se);
atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg);
atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg);
}
@@ -2898,7 +3362,16 @@ static int idle_balance(struct rq *this_rq);
#else /* CONFIG_SMP */
-static inline void update_load_avg(struct sched_entity *se, int update_tg) {}
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
+{
+ return 0;
+}
+
+#define UPDATE_TG 0x0
+#define SKIP_AGE_LOAD 0x0
+
+static inline void update_load_avg(struct sched_entity *se, int not_used1){}
static inline void
enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
static inline void
@@ -2962,6 +3435,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
trace_sched_stat_blocked(tsk, delta);
+ trace_sched_blocked_reason(tsk);
/*
* Blocking time is in units of nanosecs, so shift by
@@ -3040,9 +3514,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+ update_load_avg(se, UPDATE_TG);
enqueue_entity_load_avg(cfs_rq, se);
+ update_cfs_shares(se);
account_entity_enqueue(cfs_rq, se);
- update_cfs_shares(cfs_rq);
if (flags & ENQUEUE_WAKEUP) {
place_entity(cfs_rq, se, 0);
@@ -3115,6 +3590,16 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
+
+ /*
+ * When dequeuing a sched_entity, we must:
+ * - Update loads to have both entity and cfs_rq synced with now.
+ * - Substract its load from the cfs_rq->runnable_avg.
+ * - Substract its previous weight from cfs_rq->load.weight.
+ * - For group entity, update its weight to reflect the new share
+ * of its group cfs_rq.
+ */
+ update_load_avg(se, UPDATE_TG);
dequeue_entity_load_avg(cfs_rq, se);
update_stats_dequeue(cfs_rq, se);
@@ -3150,7 +3635,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
return_cfs_rq_runtime(cfs_rq);
update_min_vruntime(cfs_rq);
- update_cfs_shares(cfs_rq);
+ update_cfs_shares(se);
}
/*
@@ -3205,7 +3690,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
*/
update_stats_wait_end(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
- update_load_avg(se, 1);
+ update_load_avg(se, UPDATE_TG);
}
update_stats_curr_start(cfs_rq, se);
@@ -3321,8 +3806,8 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
/*
* Ensure that runnable average is periodically updated.
*/
- update_load_avg(curr, 1);
- update_cfs_shares(cfs_rq);
+ update_load_avg(curr, UPDATE_TG);
+ update_cfs_shares(curr);
#ifdef CONFIG_SCHED_HRTICK
/*
@@ -3623,9 +4108,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
/*
* Add to the _head_ of the list, so that an already-started
- * distribute_cfs_runtime will not see us
+ * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
+ * not running add to the tail so that later runqueues don't get starved.
*/
- list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ if (cfs_b->distribute_running)
+ list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ else
+ list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
/*
* If we're the first throttled task, make sure the bandwidth
@@ -3768,14 +4257,16 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
* in us over-using our runtime if it is all used during this loop, but
* only by limited amounts in that extreme case.
*/
- while (throttled && cfs_b->runtime > 0) {
+ while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
runtime = cfs_b->runtime;
+ cfs_b->distribute_running = 1;
raw_spin_unlock(&cfs_b->lock);
/* we can't nest cfs_b->lock while distributing bandwidth */
runtime = distribute_cfs_runtime(cfs_b, runtime,
runtime_expires);
raw_spin_lock(&cfs_b->lock);
+ cfs_b->distribute_running = 0;
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
cfs_b->runtime -= min(runtime, cfs_b->runtime);
@@ -3886,6 +4377,11 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
/* confirm we're still not at a refresh boundary */
raw_spin_lock(&cfs_b->lock);
+ if (cfs_b->distribute_running) {
+ raw_spin_unlock(&cfs_b->lock);
+ return;
+ }
+
if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
raw_spin_unlock(&cfs_b->lock);
return;
@@ -3895,6 +4391,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
runtime = cfs_b->runtime;
expires = cfs_b->runtime_expires;
+ if (runtime)
+ cfs_b->distribute_running = 1;
+
raw_spin_unlock(&cfs_b->lock);
if (!runtime)
@@ -3905,6 +4404,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
raw_spin_lock(&cfs_b->lock);
if (expires == cfs_b->runtime_expires)
cfs_b->runtime -= min(runtime, cfs_b->runtime);
+ cfs_b->distribute_running = 0;
raw_spin_unlock(&cfs_b->lock);
}
@@ -3918,6 +4418,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
if (!cfs_bandwidth_used())
return;
+ /* Synchronize hierarchical throttle counter: */
+ if (unlikely(!cfs_rq->throttle_uptodate)) {
+ struct rq *rq = rq_of(cfs_rq);
+ struct cfs_rq *pcfs_rq;
+ struct task_group *tg;
+
+ cfs_rq->throttle_uptodate = 1;
+
+ /* Get closest up-to-date node, because leaves go first: */
+ for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+ pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+ if (pcfs_rq->throttle_uptodate)
+ break;
+ }
+ if (tg) {
+ cfs_rq->throttle_count = pcfs_rq->throttle_count;
+ cfs_rq->throttled_clock_task = rq_clock_task(rq);
+ }
+ }
+
/* an active group must be handled by the update_curr()->put() path */
if (!cfs_rq->runtime_enabled || cfs_rq->curr)
return;
@@ -3962,12 +4482,15 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
return HRTIMER_NORESTART;
}
+extern const u64 max_cfs_quota_period;
+
static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
{
struct cfs_bandwidth *cfs_b =
container_of(timer, struct cfs_bandwidth, period_timer);
int overrun;
int idle = 0;
+ int count = 0;
raw_spin_lock(&cfs_b->lock);
for (;;) {
@@ -3975,6 +4498,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
if (!overrun)
break;
+ if (++count > 3) {
+ u64 new, old = ktime_to_ns(cfs_b->period);
+
+ new = (old * 147) / 128; /* ~115% */
+ new = min(new, max_cfs_quota_period);
+
+ cfs_b->period = ns_to_ktime(new);
+
+ /* since max is 1s, this is limited to 1e9^2, which fits in u64 */
+ cfs_b->quota *= new;
+ cfs_b->quota = div64_u64(cfs_b->quota, old);
+
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(new, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+
+ /* reset count so we don't come right back in here */
+ count = 0;
+ }
+
idle = do_sched_cfs_period_timer(cfs_b, overrun);
}
if (idle)
@@ -3996,6 +4541,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
cfs_b->period_timer.function = sched_cfs_period_timer;
hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->slack_timer.function = sched_cfs_slack_timer;
+ cfs_b->distribute_running = 0;
}
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
@@ -4157,6 +4703,14 @@ static inline void hrtick_update(struct rq *rq)
}
#endif
+#ifdef CONFIG_SMP
+static bool __cpu_overutilized(int cpu, int delta);
+static bool cpu_overutilized(int cpu);
+unsigned long boosted_cpu_util(int cpu);
+#else
+#define boosted_cpu_util(cpu) cpu_util_freq(cpu)
+#endif
+
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
@@ -4167,6 +4721,17 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
+#ifdef CONFIG_SMP
+ int task_new = flags & ENQUEUE_WAKEUP_NEW;
+#endif
+
+ /*
+ * If in_iowait is set, the code below may not trigger any cpufreq
+ * utilization updates, so do it here explicitly with the IOWAIT flag
+ * passed.
+ */
+ if (p->in_iowait)
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
for_each_sched_entity(se) {
if (se->on_rq)
@@ -4179,10 +4744,11 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
*
* note: in the case of encountering a throttled cfs_rq we will
* post the final h_nr_running increment below.
- */
+ */
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running++;
+ walt_inc_cfs_cumulative_runnable_avg(cfs_rq, p);
flags = ENQUEUE_WAKEUP;
}
@@ -4190,17 +4756,49 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running++;
+ walt_inc_cfs_cumulative_runnable_avg(cfs_rq, p);
if (cfs_rq_throttled(cfs_rq))
break;
- update_load_avg(se, 1);
- update_cfs_shares(cfs_rq);
+ update_load_avg(se, UPDATE_TG);
+ update_cfs_shares(se);
}
if (!se)
add_nr_running(rq, 1);
+#ifdef CONFIG_SMP
+
+ /*
+ * Update SchedTune accounting.
+ *
+ * We do it before updating the CPU capacity to ensure the
+ * boost value of the current task is accounted for in the
+ * selection of the OPP.
+ *
+ * We do it also in the case where we enqueue a throttled task;
+ * we could argue that a throttled task should not boost a CPU,
+ * however:
+ * a) properly implementing CPU boosting considering throttled
+ * tasks will increase a lot the complexity of the solution
+ * b) it's not easy to quantify the benefits introduced by
+ * such a more complex solution.
+ * Thus, for the time being we go for the simple solution and boost
+ * also for throttled RQs.
+ */
+ schedtune_enqueue_task(p, cpu_of(rq));
+
+ if (!se) {
+ walt_inc_cumulative_runnable_avg(rq, p);
+ if (!task_new && !rq->rd->overutilized &&
+ cpu_overutilized(rq->cpu)) {
+ rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
+ }
+
+#endif /* CONFIG_SMP */
hrtick_update(rq);
}
@@ -4230,18 +4828,18 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
if (cfs_rq_throttled(cfs_rq))
break;
cfs_rq->h_nr_running--;
+ walt_dec_cfs_cumulative_runnable_avg(cfs_rq, p);
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
+ /* Avoid re-evaluating load for this entity: */
+ se = parent_entity(se);
/*
* Bias pick_next to pick a task from this cfs_rq, as
* p is sleeping when it is within its sched_slice.
*/
- if (task_sleep && parent_entity(se))
- set_next_buddy(parent_entity(se));
-
- /* avoid re-evaluating load for this entity */
- se = parent_entity(se);
+ if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+ set_next_buddy(se);
break;
}
flags |= DEQUEUE_SLEEP;
@@ -4250,17 +4848,33 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running--;
+ walt_dec_cfs_cumulative_runnable_avg(cfs_rq, p);
if (cfs_rq_throttled(cfs_rq))
break;
- update_load_avg(se, 1);
- update_cfs_shares(cfs_rq);
+ update_load_avg(se, UPDATE_TG);
+ update_cfs_shares(se);
}
if (!se)
sub_nr_running(rq, 1);
+#ifdef CONFIG_SMP
+
+ /*
+ * Update SchedTune accounting
+ *
+ * We do it before updating the CPU capacity to ensure the
+ * boost value of the current task is accounted for in the
+ * selection of the OPP.
+ */
+ schedtune_dequeue_task(p, cpu_of(rq));
+
+ if (!se)
+ walt_dec_cumulative_runnable_avg(rq, p);
+#endif /* CONFIG_SMP */
+
hrtick_update(rq);
}
@@ -4487,15 +5101,6 @@ static unsigned long target_load(int cpu, int type)
return max(rq->cpu_load[type-1], total);
}
-static unsigned long capacity_of(int cpu)
-{
- return cpu_rq(cpu)->cpu_capacity;
-}
-
-static unsigned long capacity_orig_of(int cpu)
-{
- return cpu_rq(cpu)->cpu_capacity_orig;
-}
static unsigned long cpu_avg_load_per_task(int cpu)
{
@@ -4670,6 +5275,525 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
#endif
/*
+ * Returns the current capacity of cpu after applying both
+ * cpu and freq scaling.
+ */
+unsigned long capacity_curr_of(int cpu)
+{
+ return cpu_rq(cpu)->cpu_capacity_orig *
+ arch_scale_freq_capacity(NULL, cpu)
+ >> SCHED_CAPACITY_SHIFT;
+}
+
+static inline bool energy_aware(void)
+{
+ return sched_feat(ENERGY_AWARE);
+}
+
+struct energy_env {
+ struct sched_group *sg_top;
+ struct sched_group *sg_cap;
+ int cap_idx;
+ int util_delta;
+ int src_cpu;
+ int dst_cpu;
+ int trg_cpu;
+ int energy;
+ int payoff;
+ struct task_struct *task;
+ struct {
+ int before;
+ int after;
+ int delta;
+ int diff;
+ } nrg;
+ struct {
+ int before;
+ int after;
+ int delta;
+ } cap;
+};
+
+static int cpu_util_wake(int cpu, struct task_struct *p);
+
+/*
+ * __cpu_norm_util() returns the cpu util relative to a specific capacity,
+ * i.e. it's busy ratio, in the range [0..SCHED_LOAD_SCALE], which is useful for
+ * energy calculations.
+ *
+ * Since util is a scale-invariant utilization defined as:
+ *
+ * util ~ (curr_freq/max_freq)*1024 * capacity_orig/1024 * running_time/time
+ *
+ * the normalized util can be found using the specific capacity.
+ *
+ * capacity = capacity_orig * curr_freq/max_freq
+ *
+ * norm_util = running_time/time ~ util/capacity
+ */
+static unsigned long __cpu_norm_util(unsigned long util, unsigned long capacity)
+{
+ if (util >= capacity)
+ return SCHED_CAPACITY_SCALE;
+
+ return (util << SCHED_CAPACITY_SHIFT)/capacity;
+}
+
+static unsigned long group_max_util(struct energy_env *eenv)
+{
+ unsigned long max_util = 0;
+ unsigned long util;
+ int cpu;
+
+ for_each_cpu(cpu, sched_group_cpus(eenv->sg_cap)) {
+ util = cpu_util_wake(cpu, eenv->task);
+
+ /*
+ * If we are looking at the target CPU specified by the eenv,
+ * then we should add the (estimated) utilization of the task
+ * assuming we will wake it up on that CPU.
+ */
+ if (unlikely(cpu == eenv->trg_cpu))
+ util += eenv->util_delta;
+
+ max_util = max(max_util, util);
+ }
+
+ return max_util;
+}
+
+/*
+ * group_norm_util() returns the approximated group util relative to it's
+ * current capacity (busy ratio), in the range [0..SCHED_LOAD_SCALE], for use
+ * in energy calculations.
+ *
+ * Since task executions may or may not overlap in time in the group the true
+ * normalized util is between MAX(cpu_norm_util(i)) and SUM(cpu_norm_util(i))
+ * when iterating over all CPUs in the group.
+ * The latter estimate is used as it leads to a more pessimistic energy
+ * estimate (more busy).
+ */
+static unsigned
+long group_norm_util(struct energy_env *eenv, struct sched_group *sg)
+{
+ unsigned long capacity = sg->sge->cap_states[eenv->cap_idx].cap;
+ unsigned long util, util_sum = 0;
+ int cpu;
+
+ for_each_cpu(cpu, sched_group_cpus(sg)) {
+ util = cpu_util_wake(cpu, eenv->task);
+
+ /*
+ * If we are looking at the target CPU specified by the eenv,
+ * then we should add the (estimated) utilization of the task
+ * assuming we will wake it up on that CPU.
+ */
+ if (unlikely(cpu == eenv->trg_cpu))
+ util += eenv->util_delta;
+
+ util_sum += __cpu_norm_util(util, capacity);
+ }
+
+ return min_t(unsigned long, util_sum, SCHED_CAPACITY_SCALE);
+}
+
+static int find_new_capacity(struct energy_env *eenv,
+ const struct sched_group_energy * const sge)
+{
+ int idx, max_idx = sge->nr_cap_states - 1;
+ unsigned long util = group_max_util(eenv);
+
+ /* default is max_cap if we don't find a match */
+ eenv->cap_idx = max_idx;
+
+ for (idx = 0; idx < sge->nr_cap_states; idx++) {
+ if (sge->cap_states[idx].cap >= util) {
+ eenv->cap_idx = idx;
+ break;
+ }
+ }
+
+ return eenv->cap_idx;
+}
+
+static int group_idle_state(struct energy_env *eenv, struct sched_group *sg)
+{
+ int i, state = INT_MAX;
+ int src_in_grp, dst_in_grp;
+ long grp_util = 0;
+
+ /* Find the shallowest idle state in the sched group. */
+ for_each_cpu(i, sched_group_cpus(sg))
+ state = min(state, idle_get_state_idx(cpu_rq(i)));
+
+ /* Take non-cpuidle idling into account (active idle/arch_cpu_idle()) */
+ state++;
+
+ src_in_grp = cpumask_test_cpu(eenv->src_cpu, sched_group_cpus(sg));
+ dst_in_grp = cpumask_test_cpu(eenv->dst_cpu, sched_group_cpus(sg));
+ if (src_in_grp == dst_in_grp) {
+ /* both CPUs under consideration are in the same group or not in
+ * either group, migration should leave idle state the same.
+ */
+ goto end;
+ }
+
+ /*
+ * Try to estimate if a deeper idle state is
+ * achievable when we move the task.
+ */
+ for_each_cpu(i, sched_group_cpus(sg)) {
+ grp_util += cpu_util_wake(i, eenv->task);
+ if (unlikely(i == eenv->trg_cpu))
+ grp_util += eenv->util_delta;
+ }
+
+ if (grp_util <=
+ ((long)sg->sgc->max_capacity * (int)sg->group_weight)) {
+ /* after moving, this group is at most partly
+ * occupied, so it should have some idle time.
+ */
+ int max_idle_state_idx = sg->sge->nr_idle_states - 2;
+ int new_state = grp_util * max_idle_state_idx;
+ if (grp_util <= 0)
+ /* group will have no util, use lowest state */
+ new_state = max_idle_state_idx + 1;
+ else {
+ /* for partially idle, linearly map util to idle
+ * states, excluding the lowest one. This does not
+ * correspond to the state we expect to enter in
+ * reality, but an indication of what might happen.
+ */
+ new_state = min(max_idle_state_idx, (int)
+ (new_state / sg->sgc->max_capacity));
+ new_state = max_idle_state_idx - new_state;
+ }
+ state = new_state;
+ } else {
+ /* After moving, the group will be fully occupied
+ * so assume it will not be idle at all.
+ */
+ state = 0;
+ }
+end:
+ return state;
+}
+
+/*
+ * sched_group_energy(): Computes the absolute energy consumption of cpus
+ * belonging to the sched_group including shared resources shared only by
+ * members of the group. Iterates over all cpus in the hierarchy below the
+ * sched_group starting from the bottom working it's way up before going to
+ * the next cpu until all cpus are covered at all levels. The current
+ * implementation is likely to gather the same util statistics multiple times.
+ * This can probably be done in a faster but more complex way.
+ * Note: sched_group_energy() may fail when racing with sched_domain updates.
+ */
+static int sched_group_energy(struct energy_env *eenv)
+{
+ struct cpumask visit_cpus;
+ u64 total_energy = 0;
+ int cpu_count;
+
+ WARN_ON(!eenv->sg_top->sge);
+
+ cpumask_copy(&visit_cpus, sched_group_cpus(eenv->sg_top));
+ /* If a cpu is hotplugged in while we are in this function,
+ * it does not appear in the existing visit_cpus mask
+ * which came from the sched_group pointer of the
+ * sched_domain pointed at by sd_ea for either the prev
+ * or next cpu and was dereferenced in __energy_diff.
+ * Since we will dereference sd_scs later as we iterate
+ * through the CPUs we expect to visit, new CPUs can
+ * be present which are not in the visit_cpus mask.
+ * Guard this with cpu_count.
+ */
+ cpu_count = cpumask_weight(&visit_cpus);
+
+ while (!cpumask_empty(&visit_cpus)) {
+ struct sched_group *sg_shared_cap = NULL;
+ int cpu = cpumask_first(&visit_cpus);
+ struct sched_domain *sd;
+
+ /*
+ * Is the group utilization affected by cpus outside this
+ * sched_group?
+ * This sd may have groups with cpus which were not present
+ * when we took visit_cpus.
+ */
+ sd = rcu_dereference(per_cpu(sd_scs, cpu));
+
+ if (sd && sd->parent)
+ sg_shared_cap = sd->parent->groups;
+
+ for_each_domain(cpu, sd) {
+ struct sched_group *sg = sd->groups;
+
+ /* Has this sched_domain already been visited? */
+ if (sd->child && group_first_cpu(sg) != cpu)
+ break;
+
+ do {
+ unsigned long group_util;
+ int sg_busy_energy, sg_idle_energy;
+ int cap_idx, idle_idx;
+
+ if (sg_shared_cap && sg_shared_cap->group_weight >= sg->group_weight)
+ eenv->sg_cap = sg_shared_cap;
+ else
+ eenv->sg_cap = sg;
+
+ cap_idx = find_new_capacity(eenv, sg->sge);
+
+ if (sg->group_weight == 1) {
+ /* Remove capacity of src CPU (before task move) */
+ if (eenv->trg_cpu == eenv->src_cpu &&
+ cpumask_test_cpu(eenv->src_cpu, sched_group_cpus(sg))) {
+ eenv->cap.before = sg->sge->cap_states[cap_idx].cap;
+ eenv->cap.delta -= eenv->cap.before;
+ }
+ /* Add capacity of dst CPU (after task move) */
+ if (eenv->trg_cpu == eenv->dst_cpu &&
+ cpumask_test_cpu(eenv->dst_cpu, sched_group_cpus(sg))) {
+ eenv->cap.after = sg->sge->cap_states[cap_idx].cap;
+ eenv->cap.delta += eenv->cap.after;
+ }
+ }
+
+ idle_idx = group_idle_state(eenv, sg);
+ group_util = group_norm_util(eenv, sg);
+
+ sg_busy_energy = (group_util * sg->sge->cap_states[cap_idx].power);
+ sg_idle_energy = ((SCHED_LOAD_SCALE-group_util)
+ * sg->sge->idle_states[idle_idx].power);
+
+ total_energy += sg_busy_energy + sg_idle_energy;
+
+ if (!sd->child) {
+ /*
+ * cpu_count here is the number of
+ * cpus we expect to visit in this
+ * calculation. If we race against
+ * hotplug, we can have extra cpus
+ * added to the groups we are
+ * iterating which do not appear in
+ * the visit_cpus mask. In that case
+ * we are not able to calculate energy
+ * without restarting so we will bail
+ * out and use prev_cpu this time.
+ */
+ if (!cpu_count)
+ return -EINVAL;
+ cpumask_xor(&visit_cpus, &visit_cpus, sched_group_cpus(sg));
+ cpu_count--;
+ }
+
+ if (cpumask_equal(sched_group_cpus(sg), sched_group_cpus(eenv->sg_top)))
+ goto next_cpu;
+
+ } while (sg = sg->next, sg != sd->groups);
+ }
+
+ /*
+ * If we raced with hotplug and got an sd NULL-pointer;
+ * returning a wrong energy estimation is better than
+ * entering an infinite loop.
+ * Specifically: If a cpu is unplugged after we took
+ * the visit_cpus mask, it no longer has an sd_scs
+ * pointer, so when we dereference it, we get NULL.
+ */
+ if (cpumask_test_cpu(cpu, &visit_cpus))
+ return -EINVAL;
+next_cpu:
+ cpumask_clear_cpu(cpu, &visit_cpus);
+ continue;
+ }
+
+ eenv->energy = total_energy >> SCHED_CAPACITY_SHIFT;
+ return 0;
+}
+
+static inline bool cpu_in_sg(struct sched_group *sg, int cpu)
+{
+ return cpu != -1 && cpumask_test_cpu(cpu, sched_group_cpus(sg));
+}
+
+static inline unsigned long task_util(struct task_struct *p);
+
+/*
+ * energy_diff(): Estimate the energy impact of changing the utilization
+ * distribution. eenv specifies the change: utilisation amount, source, and
+ * destination cpu. Source or destination cpu may be -1 in which case the
+ * utilization is removed from or added to the system (e.g. task wake-up). If
+ * both are specified, the utilization is migrated.
+ */
+static inline int __energy_diff(struct energy_env *eenv)
+{
+ struct sched_domain *sd;
+ struct sched_group *sg;
+ int sd_cpu = -1, energy_before = 0, energy_after = 0;
+ int diff, margin;
+
+ struct energy_env eenv_before = {
+ .util_delta = task_util(eenv->task),
+ .src_cpu = eenv->src_cpu,
+ .dst_cpu = eenv->dst_cpu,
+ .trg_cpu = eenv->src_cpu,
+ .nrg = { 0, 0, 0, 0},
+ .cap = { 0, 0, 0 },
+ .task = eenv->task,
+ };
+
+ if (eenv->src_cpu == eenv->dst_cpu)
+ return 0;
+
+ sd_cpu = (eenv->src_cpu != -1) ? eenv->src_cpu : eenv->dst_cpu;
+ sd = rcu_dereference(per_cpu(sd_ea, sd_cpu));
+
+ if (!sd)
+ return 0; /* Error */
+
+ sg = sd->groups;
+
+ do {
+ if (cpu_in_sg(sg, eenv->src_cpu) || cpu_in_sg(sg, eenv->dst_cpu)) {
+ eenv_before.sg_top = eenv->sg_top = sg;
+
+ if (sched_group_energy(&eenv_before))
+ return 0; /* Invalid result abort */
+ energy_before += eenv_before.energy;
+
+ /* Keep track of SRC cpu (before) capacity */
+ eenv->cap.before = eenv_before.cap.before;
+ eenv->cap.delta = eenv_before.cap.delta;
+
+ if (sched_group_energy(eenv))
+ return 0; /* Invalid result abort */
+ energy_after += eenv->energy;
+ }
+ } while (sg = sg->next, sg != sd->groups);
+
+ eenv->nrg.before = energy_before;
+ eenv->nrg.after = energy_after;
+ eenv->nrg.diff = eenv->nrg.after - eenv->nrg.before;
+ eenv->payoff = 0;
+#ifndef CONFIG_SCHED_TUNE
+ trace_sched_energy_diff(eenv->task,
+ eenv->src_cpu, eenv->dst_cpu, eenv->util_delta,
+ eenv->nrg.before, eenv->nrg.after, eenv->nrg.diff,
+ eenv->cap.before, eenv->cap.after, eenv->cap.delta,
+ eenv->nrg.delta, eenv->payoff);
+#endif
+ /*
+ * Dead-zone margin preventing too many migrations.
+ */
+
+ margin = eenv->nrg.before >> 6; /* ~1.56% */
+
+ diff = eenv->nrg.after - eenv->nrg.before;
+
+ eenv->nrg.diff = (abs(diff) < margin) ? 0 : eenv->nrg.diff;
+
+ return eenv->nrg.diff;
+}
+
+#ifdef CONFIG_SCHED_TUNE
+
+struct target_nrg schedtune_target_nrg;
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+extern bool schedtune_initialized;
+#endif /* CONFIG_CGROUP_SCHEDTUNE */
+
+/*
+ * System energy normalization
+ * Returns the normalized value, in the range [0..SCHED_CAPACITY_SCALE],
+ * corresponding to the specified energy variation.
+ */
+static inline int
+normalize_energy(int energy_diff)
+{
+ u32 normalized_nrg;
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+ /* during early setup, we don't know the extents */
+ if (unlikely(!schedtune_initialized))
+ return energy_diff < 0 ? -1 : 1 ;
+#endif /* CONFIG_CGROUP_SCHEDTUNE */
+
+#ifdef CONFIG_SCHED_DEBUG
+ {
+ int max_delta;
+
+ /* Check for boundaries */
+ max_delta = schedtune_target_nrg.max_power;
+ max_delta -= schedtune_target_nrg.min_power;
+ WARN_ON(abs(energy_diff) >= max_delta);
+ }
+#endif
+
+ /* Do scaling using positive numbers to increase the range */
+ normalized_nrg = (energy_diff < 0) ? -energy_diff : energy_diff;
+
+ /* Scale by energy magnitude */
+ normalized_nrg <<= SCHED_CAPACITY_SHIFT;
+
+ /* Normalize on max energy for target platform */
+ normalized_nrg = reciprocal_divide(
+ normalized_nrg, schedtune_target_nrg.rdiv);
+
+ return (energy_diff < 0) ? -normalized_nrg : normalized_nrg;
+}
+
+static inline int
+energy_diff(struct energy_env *eenv)
+{
+ int boost = schedtune_task_boost(eenv->task);
+ int nrg_delta;
+
+ /* Conpute "absolute" energy diff */
+ __energy_diff(eenv);
+
+ /* Return energy diff when boost margin is 0 */
+ if (boost == 0) {
+ trace_sched_energy_diff(eenv->task,
+ eenv->src_cpu, eenv->dst_cpu, eenv->util_delta,
+ eenv->nrg.before, eenv->nrg.after, eenv->nrg.diff,
+ eenv->cap.before, eenv->cap.after, eenv->cap.delta,
+ 0, -eenv->nrg.diff);
+ return eenv->nrg.diff;
+ }
+
+ /* Compute normalized energy diff */
+ nrg_delta = normalize_energy(eenv->nrg.diff);
+ eenv->nrg.delta = nrg_delta;
+
+ eenv->payoff = schedtune_accept_deltas(
+ eenv->nrg.delta,
+ eenv->cap.delta,
+ eenv->task);
+
+ trace_sched_energy_diff(eenv->task,
+ eenv->src_cpu, eenv->dst_cpu, eenv->util_delta,
+ eenv->nrg.before, eenv->nrg.after, eenv->nrg.diff,
+ eenv->cap.before, eenv->cap.after, eenv->cap.delta,
+ eenv->nrg.delta, eenv->payoff);
+
+ /*
+ * When SchedTune is enabled, the energy_diff() function will return
+ * the computed energy payoff value. Since the energy_diff() return
+ * value is expected to be negative by its callers, this evaluation
+ * function return a negative value each time the evaluation return a
+ * positive payoff, which is the condition for the acceptance of
+ * a scheduling decision
+ */
+ return -eenv->payoff;
+}
+#else /* CONFIG_SCHED_TUNE */
+#define energy_diff(eenv) __energy_diff(eenv)
+#endif
+
+/*
* Detect M:N waker/wakee relationships via a switching-frequency heuristic.
* A waker of many should wake a different task than the one last awakened
* at a frequency roughly N times higher than one of its wakees. In order
@@ -4681,31 +5805,34 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
* being client/server, worker/dispatcher, interrupt source or whatever is
* irrelevant, spread criteria is apparent partner count exceeds socket size.
*/
-static int wake_wide(struct task_struct *p)
+static int wake_wide(struct task_struct *p, int sibling_count_hint)
{
unsigned int master = current->wakee_flips;
unsigned int slave = p->wakee_flips;
- int factor = this_cpu_read(sd_llc_size);
+ int llc_size = this_cpu_read(sd_llc_size);
+
+ if (sibling_count_hint >= llc_size)
+ return 1;
if (master < slave)
swap(master, slave);
- if (slave < factor || master < slave * factor)
+ if (slave < llc_size || master < slave * llc_size)
return 0;
return 1;
}
-static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
+static int wake_affine(struct sched_domain *sd, struct task_struct *p,
+ int prev_cpu, int sync)
{
s64 this_load, load;
s64 this_eff_load, prev_eff_load;
- int idx, this_cpu, prev_cpu;
+ int idx, this_cpu;
struct task_group *tg;
unsigned long weight;
int balanced;
idx = sd->wake_idx;
this_cpu = smp_processor_id();
- prev_cpu = task_cpu(p);
load = source_load(prev_cpu, idx);
this_load = target_load(this_cpu, idx);
@@ -4760,16 +5887,166 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
return 1;
}
+static inline unsigned long task_util(struct task_struct *p)
+{
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_task_util) {
+ unsigned long demand = p->ravg.demand;
+ return (demand << 10) / walt_ravg_window;
+ }
+#endif
+ return p->se.avg.util_avg;
+}
+
+static inline unsigned long boosted_task_util(struct task_struct *task);
+
+static inline bool __task_fits(struct task_struct *p, int cpu, int util)
+{
+ unsigned long capacity = capacity_of(cpu);
+
+ util += boosted_task_util(p);
+
+ return (capacity * 1024) > (util * capacity_margin);
+}
+
+static inline bool task_fits_max(struct task_struct *p, int cpu)
+{
+ unsigned long capacity = capacity_of(cpu);
+ unsigned long max_capacity = cpu_rq(cpu)->rd->max_cpu_capacity.val;
+
+ if (capacity == max_capacity)
+ return true;
+
+ if (capacity * capacity_margin > max_capacity * 1024)
+ return true;
+
+ return __task_fits(p, cpu, 0);
+}
+
+static bool __cpu_overutilized(int cpu, int delta)
+{
+ return (capacity_of(cpu) * 1024) < ((cpu_util(cpu) + delta) * capacity_margin);
+}
+
+static bool cpu_overutilized(int cpu)
+{
+ return __cpu_overutilized(cpu, 0);
+}
+
+#ifdef CONFIG_SCHED_TUNE
+
+struct reciprocal_value schedtune_spc_rdiv;
+
+static long
+schedtune_margin(unsigned long signal, long boost)
+{
+ long long margin = 0;
+
+ /*
+ * Signal proportional compensation (SPC)
+ *
+ * The Boost (B) value is used to compute a Margin (M) which is
+ * proportional to the complement of the original Signal (S):
+ * M = B * (SCHED_CAPACITY_SCALE - S)
+ * The obtained M could be used by the caller to "boost" S.
+ */
+ if (boost >= 0) {
+ margin = SCHED_CAPACITY_SCALE - signal;
+ margin *= boost;
+ } else
+ margin = -signal * boost;
+
+ margin = reciprocal_divide(margin, schedtune_spc_rdiv);
+
+ if (boost < 0)
+ margin *= -1;
+ return margin;
+}
+
+static inline int
+schedtune_cpu_margin(unsigned long util, int cpu)
+{
+ int boost = schedtune_cpu_boost(cpu);
+
+ if (boost == 0)
+ return 0;
+
+ return schedtune_margin(util, boost);
+}
+
+static inline long
+schedtune_task_margin(struct task_struct *task)
+{
+ int boost = schedtune_task_boost(task);
+ unsigned long util;
+ long margin;
+
+ if (boost == 0)
+ return 0;
+
+ util = task_util(task);
+ margin = schedtune_margin(util, boost);
+
+ return margin;
+}
+
+#else /* CONFIG_SCHED_TUNE */
+
+static inline int
+schedtune_cpu_margin(unsigned long util, int cpu)
+{
+ return 0;
+}
+
+static inline int
+schedtune_task_margin(struct task_struct *task)
+{
+ return 0;
+}
+
+#endif /* CONFIG_SCHED_TUNE */
+
+unsigned long
+boosted_cpu_util(int cpu)
+{
+ unsigned long util = cpu_util_freq(cpu);
+ long margin = schedtune_cpu_margin(util, cpu);
+
+ trace_sched_boost_cpu(cpu, util, margin);
+
+ return util + margin;
+}
+
+static inline unsigned long
+boosted_task_util(struct task_struct *task)
+{
+ unsigned long util = task_util(task);
+ long margin = schedtune_task_margin(task);
+
+ trace_sched_boost_task(task, util, margin);
+
+ return util + margin;
+}
+
+static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+{
+ return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0);
+}
+
/*
* find_idlest_group finds and returns the least busy CPU group within the
* domain.
+ *
+ * Assumes p is allowed on at least one CPU in sd.
*/
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
int this_cpu, int sd_flag)
{
struct sched_group *idlest = NULL, *group = sd->groups;
- unsigned long min_load = ULONG_MAX, this_load = 0;
+ struct sched_group *most_spare_sg = NULL;
+ unsigned long min_load = ULONG_MAX, this_load = ULONG_MAX;
+ unsigned long most_spare = 0, this_spare = 0;
int load_idx = sd->forkexec_idx;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
@@ -4777,7 +6054,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
load_idx = sd->wake_idx;
do {
- unsigned long load, avg_load;
+ unsigned long load, avg_load, spare_cap, max_spare_cap;
int local_group;
int i;
@@ -4789,8 +6066,12 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
local_group = cpumask_test_cpu(this_cpu,
sched_group_cpus(group));
- /* Tally up the load of all CPUs in the group */
+ /*
+ * Tally up the load of all CPUs in the group and find
+ * the group containing the CPU with most spare capacity.
+ */
avg_load = 0;
+ max_spare_cap = 0;
for_each_cpu(i, sched_group_cpus(group)) {
/* Bias balancing toward cpus of our domain */
@@ -4800,6 +6081,11 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
load = target_load(i, load_idx);
avg_load += load;
+
+ spare_cap = capacity_spare_wake(i, p);
+
+ if (spare_cap > max_spare_cap)
+ max_spare_cap = spare_cap;
}
/* Adjust by relative CPU capacity of the group */
@@ -4807,22 +6093,51 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
if (local_group) {
this_load = avg_load;
- } else if (avg_load < min_load) {
- min_load = avg_load;
- idlest = group;
+ this_spare = max_spare_cap;
+ } else {
+ if (avg_load < min_load) {
+ min_load = avg_load;
+ idlest = group;
+ }
+
+ if (most_spare < max_spare_cap) {
+ most_spare = max_spare_cap;
+ most_spare_sg = group;
+ }
}
} while (group = group->next, group != sd->groups);
+ /*
+ * The cross-over point between using spare capacity or least load
+ * is too conservative for high utilization tasks on partially
+ * utilized systems if we require spare_capacity > task_util(p),
+ * so we allow for some task stuffing by using
+ * spare_capacity > task_util(p)/2.
+ *
+ * Spare capacity can't be used for fork because the utilization has
+ * not been set yet, we must first select a rq to compute the initial
+ * utilization.
+ */
+ if (sd_flag & SD_BALANCE_FORK)
+ goto skip_spare;
+
+ if (this_spare > task_util(p) / 2 &&
+ imbalance*this_spare > 100*most_spare)
+ return NULL;
+ else if (most_spare > task_util(p) / 2)
+ return most_spare_sg;
+
+skip_spare:
if (!idlest || 100*this_load < imbalance*min_load)
return NULL;
return idlest;
}
/*
- * find_idlest_cpu - find the idlest cpu among the cpus in group.
+ * find_idlest_group_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)
+find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
{
unsigned long load, min_load = ULONG_MAX;
unsigned int min_exit_latency = UINT_MAX;
@@ -4831,6 +6146,10 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
int shallowest_idle_cpu = -1;
int i;
+ /* Check if we have any choice: */
+ if (group->group_weight == 1)
+ return cpumask_first(sched_group_cpus(group));
+
/* Traverse only the allowed CPUs */
for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) {
if (idle_cpu(i)) {
@@ -4865,25 +6184,100 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
}
return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
+ }
+
+static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p,
+ int cpu, int prev_cpu, int sd_flag)
+{
+ int new_cpu = cpu;
+ int wu = sd_flag & SD_BALANCE_WAKE;
+ int cas_cpu = -1;
+
+ if (wu) {
+ schedstat_inc(p, se.statistics.nr_wakeups_cas_attempts);
+ schedstat_inc(this_rq(), eas_stats.cas_attempts);
+ }
+
+ if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
+ return prev_cpu;
+
+ while (sd) {
+ struct sched_group *group;
+ struct sched_domain *tmp;
+ int weight;
+
+ if (wu)
+ schedstat_inc(sd, eas_stats.cas_attempts);
+
+ if (!(sd->flags & sd_flag)) {
+ sd = sd->child;
+ continue;
+ }
+
+ group = find_idlest_group(sd, p, cpu, sd_flag);
+ if (!group) {
+ sd = sd->child;
+ continue;
+ }
+
+ new_cpu = find_idlest_group_cpu(group, p, cpu);
+ if (new_cpu == cpu) {
+ /* Now try balancing at a lower domain level of cpu */
+ sd = sd->child;
+ continue;
+ }
+
+ /* Now try balancing at a lower domain level of new_cpu */
+ cpu = cas_cpu = new_cpu;
+ weight = sd->span_weight;
+ sd = NULL;
+ for_each_domain(cpu, tmp) {
+ if (weight <= tmp->span_weight)
+ break;
+ if (tmp->flags & sd_flag)
+ sd = tmp;
+ }
+ /* while loop will break here if sd == NULL */
+ }
+
+ if (wu && (cas_cpu >= 0)) {
+ schedstat_inc(p, se.statistics.nr_wakeups_cas_count);
+ schedstat_inc(this_rq(), eas_stats.cas_count);
+ }
+
+ return new_cpu;
}
/*
* Try and locate an idle CPU in the sched_domain.
*/
-static int select_idle_sibling(struct task_struct *p, int target)
+static int select_idle_sibling(struct task_struct *p, int prev, int target)
{
struct sched_domain *sd;
struct sched_group *sg;
- int i = task_cpu(p);
-
- if (idle_cpu(target))
- return target;
+ int best_idle_cpu = -1;
+ int best_idle_cstate = INT_MAX;
+ unsigned long best_idle_capacity = ULONG_MAX;
+
+ schedstat_inc(p, se.statistics.nr_wakeups_sis_attempts);
+ schedstat_inc(this_rq(), eas_stats.sis_attempts);
+
+ if (!sysctl_sched_cstate_aware) {
+ if (idle_cpu(target)) {
+ schedstat_inc(p, se.statistics.nr_wakeups_sis_idle);
+ schedstat_inc(this_rq(), eas_stats.sis_idle);
+ return target;
+ }
- /*
- * If the prevous cpu is cache affine and idle, don't be stupid.
- */
- if (i != target && cpus_share_cache(i, target) && idle_cpu(i))
- return i;
+ /*
+ * If the prevous cpu is cache affine and idle, don't be stupid.
+ */
+ if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev)) {
+ schedstat_inc(p, se.statistics.nr_wakeups_sis_cache_affine);
+ schedstat_inc(this_rq(), eas_stats.sis_cache_affine);
+ return prev;
+ }
+ }
/*
* Otherwise, iterate the domains and find an elegible idle cpu.
@@ -4892,60 +6286,501 @@ static int select_idle_sibling(struct task_struct *p, int target)
for_each_lower_domain(sd) {
sg = sd->groups;
do {
+ int i;
if (!cpumask_intersects(sched_group_cpus(sg),
tsk_cpus_allowed(p)))
goto next;
- for_each_cpu(i, sched_group_cpus(sg)) {
- if (i == target || !idle_cpu(i))
- goto next;
- }
+ if (sysctl_sched_cstate_aware) {
+ for_each_cpu_and(i, tsk_cpus_allowed(p), sched_group_cpus(sg)) {
+ int idle_idx = idle_get_state_idx(cpu_rq(i));
+ unsigned long new_usage = boosted_task_util(p);
+ unsigned long capacity_orig = capacity_orig_of(i);
+
+ if (new_usage > capacity_orig || !idle_cpu(i))
+ goto next;
+
+ if (i == target && new_usage <= capacity_curr_of(target)) {
+ schedstat_inc(p, se.statistics.nr_wakeups_sis_suff_cap);
+ schedstat_inc(this_rq(), eas_stats.sis_suff_cap);
+ schedstat_inc(sd, eas_stats.sis_suff_cap);
+ return target;
+ }
+
+ if (idle_idx < best_idle_cstate &&
+ capacity_orig <= best_idle_capacity) {
+ best_idle_cpu = i;
+ best_idle_cstate = idle_idx;
+ best_idle_capacity = capacity_orig;
+ }
+ }
+ } else {
+ for_each_cpu(i, sched_group_cpus(sg)) {
+ if (i == target || !idle_cpu(i))
+ goto next;
+ }
- target = cpumask_first_and(sched_group_cpus(sg),
+ target = cpumask_first_and(sched_group_cpus(sg),
tsk_cpus_allowed(p));
- goto done;
+ schedstat_inc(p, se.statistics.nr_wakeups_sis_idle_cpu);
+ schedstat_inc(this_rq(), eas_stats.sis_idle_cpu);
+ schedstat_inc(sd, eas_stats.sis_idle_cpu);
+ goto done;
+ }
next:
sg = sg->next;
} while (sg != sd->groups);
}
+
+ if (best_idle_cpu >= 0)
+ target = best_idle_cpu;
+
done:
+ schedstat_inc(p, se.statistics.nr_wakeups_sis_count);
+ schedstat_inc(this_rq(), eas_stats.sis_count);
+
return target;
}
/*
- * cpu_util returns the amount of capacity of a CPU that is used by CFS
- * tasks. The unit of the return value must be the one of capacity so we can
- * compare the utilization with the capacity of the CPU that is available for
- * CFS task (ie cpu_capacity).
- *
- * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the
- * recent utilization of currently non-runnable tasks on a CPU. It represents
- * the amount of utilization of a CPU in the range [0..capacity_orig] where
- * capacity_orig is the cpu_capacity available at the highest frequency
- * (arch_scale_freq_capacity()).
- * The utilization of a CPU converges towards a sum equal to or less than the
- * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
- * the running time on this CPU scaled by capacity_curr.
- *
- * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even
- * higher than capacity_orig because of unfortunate rounding in
- * cfs.avg.util_avg or just after migrating tasks and new task wakeups until
- * the average stabilizes with the new running time. We need to check that the
- * utilization stays within the range of [0..capacity_orig] and cap it if
- * necessary. Without utilization capping, a group could be seen as overloaded
- * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of
- * available capacity. We allow utilization to overshoot capacity_curr (but not
- * capacity_orig) as it useful for predicting the capacity required after task
- * migrations (scheduler-driven DVFS).
- */
-static int cpu_util(int cpu)
-{
- unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
- unsigned long capacity = capacity_orig_of(cpu);
+ * cpu_util_wake: Compute cpu utilization with any contributions from
+ * the waking task p removed. check_for_migration() looks for a better CPU of
+ * rq->curr. For that case we should return cpu util with contributions from
+ * currently running task p removed.
+ */
+static int cpu_util_wake(int cpu, struct task_struct *p)
+{
+ unsigned long util, capacity;
+
+#ifdef CONFIG_SCHED_WALT
+ /*
+ * WALT does not decay idle tasks in the same manner
+ * as PELT, so it makes little sense to subtract task
+ * utilization from cpu utilization. Instead just use
+ * cpu_util for this case.
+ */
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util &&
+ p->state == TASK_WAKING)
+ return cpu_util(cpu);
+#endif
+ /* Task has no contribution or is new */
+ if (cpu != task_cpu(p) || !p->se.avg.last_update_time)
+ return cpu_util(cpu);
+
+ capacity = capacity_orig_of(cpu);
+ util = max_t(long, cpu_util(cpu) - task_util(p), 0);
return (util >= capacity) ? capacity : util;
}
+static int start_cpu(bool boosted)
+{
+ struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+
+ return boosted ? rd->max_cap_orig_cpu : rd->min_cap_orig_cpu;
+}
+
+static inline int find_best_target(struct task_struct *p, int *backup_cpu,
+ bool boosted, bool prefer_idle)
+{
+ unsigned long best_idle_min_cap_orig = ULONG_MAX;
+ unsigned long min_util = boosted_task_util(p);
+ unsigned long target_capacity = ULONG_MAX;
+ unsigned long min_wake_util = ULONG_MAX;
+ unsigned long target_max_spare_cap = 0;
+ unsigned long best_active_util = ULONG_MAX;
+ int best_idle_cstate = INT_MAX;
+ struct sched_domain *sd;
+ struct sched_group *sg;
+ int best_active_cpu = -1;
+ int best_idle_cpu = -1;
+ int target_cpu = -1;
+ int cpu, i;
+
+ *backup_cpu = -1;
+
+ schedstat_inc(p, se.statistics.nr_wakeups_fbt_attempts);
+ schedstat_inc(this_rq(), eas_stats.fbt_attempts);
+
+ /* Find start CPU based on boost value */
+ cpu = start_cpu(boosted);
+ if (cpu < 0) {
+ schedstat_inc(p, se.statistics.nr_wakeups_fbt_no_cpu);
+ schedstat_inc(this_rq(), eas_stats.fbt_no_cpu);
+ return -1;
+ }
+
+ /* Find SD for the start CPU */
+ sd = rcu_dereference(per_cpu(sd_ea, cpu));
+ if (!sd) {
+ schedstat_inc(p, se.statistics.nr_wakeups_fbt_no_sd);
+ schedstat_inc(this_rq(), eas_stats.fbt_no_sd);
+ return -1;
+ }
+
+ /* Scan CPUs in all SDs */
+ sg = sd->groups;
+ do {
+ for_each_cpu_and(i, tsk_cpus_allowed(p), sched_group_cpus(sg)) {
+ unsigned long capacity_curr = capacity_curr_of(i);
+ unsigned long capacity_orig = capacity_orig_of(i);
+ unsigned long wake_util, new_util;
+
+ if (!cpu_online(i))
+ continue;
+
+ if (walt_cpu_high_irqload(i))
+ continue;
+
+ /*
+ * p's blocked utilization is still accounted for on prev_cpu
+ * so prev_cpu will receive a negative bias due to the double
+ * accounting. However, the blocked utilization may be zero.
+ */
+ wake_util = cpu_util_wake(i, p);
+ new_util = wake_util + task_util(p);
+
+ /*
+ * Ensure minimum capacity to grant the required boost.
+ * The target CPU can be already at a capacity level higher
+ * than the one required to boost the task.
+ */
+ new_util = max(min_util, new_util);
+ if (new_util > capacity_orig)
+ continue;
+
+ /*
+ * Case A) Latency sensitive tasks
+ *
+ * Unconditionally favoring tasks that prefer idle CPU to
+ * improve latency.
+ *
+ * Looking for:
+ * - an idle CPU, whatever its idle_state is, since
+ * the first CPUs we explore are more likely to be
+ * reserved for latency sensitive tasks.
+ * - a non idle CPU where the task fits in its current
+ * capacity and has the maximum spare capacity.
+ * - a non idle CPU with lower contention from other
+ * tasks and running at the lowest possible OPP.
+ *
+ * The last two goals tries to favor a non idle CPU
+ * where the task can run as if it is "almost alone".
+ * A maximum spare capacity CPU is favoured since
+ * the task already fits into that CPU's capacity
+ * without waiting for an OPP chance.
+ *
+ * The following code path is the only one in the CPUs
+ * exploration loop which is always used by
+ * prefer_idle tasks. It exits the loop with wither a
+ * best_active_cpu or a target_cpu which should
+ * represent an optimal choice for latency sensitive
+ * tasks.
+ */
+ if (prefer_idle) {
+
+ /*
+ * Case A.1: IDLE CPU
+ * Return the first IDLE CPU we find.
+ */
+ if (idle_cpu(i)) {
+ schedstat_inc(p, se.statistics.nr_wakeups_fbt_pref_idle);
+ schedstat_inc(this_rq(), eas_stats.fbt_pref_idle);
+
+ trace_sched_find_best_target(p,
+ prefer_idle, min_util,
+ cpu, best_idle_cpu,
+ best_active_cpu, i);
+
+ return i;
+ }
+
+ /*
+ * Case A.2: Target ACTIVE CPU
+ * Favor CPUs with max spare capacity.
+ */
+ if ((capacity_curr > new_util) &&
+ (capacity_orig - new_util > target_max_spare_cap)) {
+ target_max_spare_cap = capacity_orig - new_util;
+ target_cpu = i;
+ continue;
+ }
+ if (target_cpu != -1)
+ continue;
+
+
+ /*
+ * Case A.3: Backup ACTIVE CPU
+ * Favor CPUs with:
+ * - lower utilization due to other tasks
+ * - lower utilization with the task in
+ */
+ if (wake_util > min_wake_util)
+ continue;
+ if (new_util > best_active_util)
+ continue;
+ min_wake_util = wake_util;
+ best_active_util = new_util;
+ best_active_cpu = i;
+ continue;
+ }
+
+ /*
+ * Enforce EAS mode
+ *
+ * For non latency sensitive tasks, skip CPUs that
+ * will be overutilized by moving the task there.
+ *
+ * The goal here is to remain in EAS mode as long as
+ * possible at least for !prefer_idle tasks.
+ */
+ if ((new_util * capacity_margin) >
+ (capacity_orig * SCHED_CAPACITY_SCALE))
+ continue;
+
+ /*
+ * Case B) Non latency sensitive tasks on IDLE CPUs.
+ *
+ * Find an optimal backup IDLE CPU for non latency
+ * sensitive tasks.
+ *
+ * Looking for:
+ * - minimizing the capacity_orig,
+ * i.e. preferring LITTLE CPUs
+ * - favoring shallowest idle states
+ * i.e. avoid to wakeup deep-idle CPUs
+ *
+ * The following code path is used by non latency
+ * sensitive tasks if IDLE CPUs are available. If at
+ * least one of such CPUs are available it sets the
+ * best_idle_cpu to the most suitable idle CPU to be
+ * selected.
+ *
+ * If idle CPUs are available, favour these CPUs to
+ * improve performances by spreading tasks.
+ * Indeed, the energy_diff() computed by the caller
+ * will take care to ensure the minimization of energy
+ * consumptions without affecting performance.
+ */
+ if (idle_cpu(i)) {
+ int idle_idx = idle_get_state_idx(cpu_rq(i));
+
+ /* Select idle CPU with lower cap_orig */
+ if (capacity_orig > best_idle_min_cap_orig)
+ continue;
+
+ /*
+ * Skip CPUs in deeper idle state, but only
+ * if they are also less energy efficient.
+ * IOW, prefer a deep IDLE LITTLE CPU vs a
+ * shallow idle big CPU.
+ */
+ if (sysctl_sched_cstate_aware &&
+ best_idle_cstate <= idle_idx)
+ continue;
+
+ /* Keep track of best idle CPU */
+ best_idle_min_cap_orig = capacity_orig;
+ best_idle_cstate = idle_idx;
+ best_idle_cpu = i;
+ continue;
+ }
+
+ /*
+ * Case C) Non latency sensitive tasks on ACTIVE CPUs.
+ *
+ * Pack tasks in the most energy efficient capacities.
+ *
+ * This task packing strategy prefers more energy
+ * efficient CPUs (i.e. pack on smaller maximum
+ * capacity CPUs) while also trying to spread tasks to
+ * run them all at the lower OPP.
+ *
+ * This assumes for example that it's more energy
+ * efficient to run two tasks on two CPUs at a lower
+ * OPP than packing both on a single CPU but running
+ * that CPU at an higher OPP.
+ *
+ * Thus, this case keep track of the CPU with the
+ * smallest maximum capacity and highest spare maximum
+ * capacity.
+ */
+
+ /* Favor CPUs with smaller capacity */
+ if (capacity_orig > target_capacity)
+ continue;
+
+ /* Favor CPUs with maximum spare capacity */
+ if ((capacity_orig - new_util) < target_max_spare_cap)
+ continue;
+
+ target_max_spare_cap = capacity_orig - new_util;
+ target_capacity = capacity_orig;
+ target_cpu = i;
+ }
+
+ } while (sg = sg->next, sg != sd->groups);
+
+ /*
+ * For non latency sensitive tasks, cases B and C in the previous loop,
+ * we pick the best IDLE CPU only if we was not able to find a target
+ * ACTIVE CPU.
+ *
+ * Policies priorities:
+ *
+ * - prefer_idle tasks:
+ *
+ * a) IDLE CPU available, we return immediately
+ * b) ACTIVE CPU where task fits and has the bigger maximum spare
+ * capacity (i.e. target_cpu)
+ * c) ACTIVE CPU with less contention due to other tasks
+ * (i.e. best_active_cpu)
+ *
+ * - NON prefer_idle tasks:
+ *
+ * a) ACTIVE CPU: target_cpu
+ * b) IDLE CPU: best_idle_cpu
+ */
+ if (target_cpu == -1)
+ target_cpu = prefer_idle
+ ? best_active_cpu
+ : best_idle_cpu;
+ else
+ *backup_cpu = prefer_idle
+ ? best_active_cpu
+ : best_idle_cpu;
+
+ trace_sched_find_best_target(p, prefer_idle, min_util, cpu,
+ best_idle_cpu, best_active_cpu,
+ target_cpu);
+
+ schedstat_inc(p, se.statistics.nr_wakeups_fbt_count);
+ schedstat_inc(this_rq(), eas_stats.fbt_count);
+
+ return target_cpu;
+}
+
+/*
+ * Disable WAKE_AFFINE in the case where task @p doesn't fit in the
+ * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
+ *
+ * In that case WAKE_AFFINE doesn't make sense and we'll let
+ * BALANCE_WAKE sort things out.
+ */
+static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
+{
+ long min_cap, max_cap;
+
+ min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
+ max_cap = cpu_rq(cpu)->rd->max_cpu_capacity.val;
+
+ /* Minimum capacity is close to max, no need to abort wake_affine */
+ if (max_cap - min_cap < max_cap >> 3)
+ return 0;
+
+ /* Bring task utilization in sync with prev_cpu */
+ sync_entity_load_avg(&p->se);
+
+ return min_cap * 1024 < task_util(p) * capacity_margin;
+}
+
+static int select_energy_cpu_brute(struct task_struct *p, int prev_cpu, int sync)
+{
+ struct sched_domain *sd;
+ int target_cpu = prev_cpu, tmp_target, tmp_backup;
+ bool boosted, prefer_idle;
+
+ schedstat_inc(p, se.statistics.nr_wakeups_secb_attempts);
+ schedstat_inc(this_rq(), eas_stats.secb_attempts);
+
+ if (sysctl_sched_sync_hint_enable && sync) {
+ int cpu = smp_processor_id();
+
+ if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) {
+ schedstat_inc(p, se.statistics.nr_wakeups_secb_sync);
+ schedstat_inc(this_rq(), eas_stats.secb_sync);
+ return cpu;
+ }
+ }
+
+ rcu_read_lock();
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+ boosted = schedtune_task_boost(p) > 0;
+ prefer_idle = schedtune_prefer_idle(p) > 0;
+#else
+ boosted = get_sysctl_sched_cfs_boost() > 0;
+ prefer_idle = 0;
+#endif
+
+ sync_entity_load_avg(&p->se);
+
+ sd = rcu_dereference(per_cpu(sd_ea, prev_cpu));
+ /* Find a cpu with sufficient capacity */
+ tmp_target = find_best_target(p, &tmp_backup, boosted, prefer_idle);
+
+ if (!sd)
+ goto unlock;
+ if (tmp_target >= 0) {
+ target_cpu = tmp_target;
+ if ((boosted || prefer_idle) && idle_cpu(target_cpu)) {
+ schedstat_inc(p, se.statistics.nr_wakeups_secb_idle_bt);
+ schedstat_inc(this_rq(), eas_stats.secb_idle_bt);
+ goto unlock;
+ }
+ }
+
+ if (target_cpu != prev_cpu) {
+ int delta = 0;
+ struct energy_env eenv = {
+ .util_delta = task_util(p),
+ .src_cpu = prev_cpu,
+ .dst_cpu = target_cpu,
+ .task = p,
+ .trg_cpu = target_cpu,
+ };
+
+
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util &&
+ p->state == TASK_WAKING)
+ delta = task_util(p);
+#endif
+ /* Not enough spare capacity on previous cpu */
+ if (__cpu_overutilized(prev_cpu, delta)) {
+ schedstat_inc(p, se.statistics.nr_wakeups_secb_insuff_cap);
+ schedstat_inc(this_rq(), eas_stats.secb_insuff_cap);
+ goto unlock;
+ }
+
+ if (energy_diff(&eenv) >= 0) {
+ /* No energy saving for target_cpu, try backup */
+ target_cpu = tmp_backup;
+ eenv.dst_cpu = target_cpu;
+ eenv.trg_cpu = target_cpu;
+ if (tmp_backup < 0 ||
+ tmp_backup == prev_cpu ||
+ energy_diff(&eenv) >= 0) {
+ schedstat_inc(p, se.statistics.nr_wakeups_secb_no_nrg_sav);
+ schedstat_inc(this_rq(), eas_stats.secb_no_nrg_sav);
+ target_cpu = prev_cpu;
+ goto unlock;
+ }
+ }
+
+ schedstat_inc(p, se.statistics.nr_wakeups_secb_nrg_sav);
+ schedstat_inc(this_rq(), eas_stats.secb_nrg_sav);
+ goto unlock;
+ }
+
+ schedstat_inc(p, se.statistics.nr_wakeups_secb_count);
+ schedstat_inc(this_rq(), eas_stats.secb_count);
+
+unlock:
+ rcu_read_unlock();
+
+ return target_cpu;
+}
+
/*
* select_task_rq_fair: Select target runqueue for the waking task in domains
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
@@ -4959,7 +6794,8 @@ static int cpu_util(int cpu)
* preempt must be disabled.
*/
static int
-select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags,
+ int sibling_count_hint)
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
int cpu = smp_processor_id();
@@ -4967,8 +6803,15 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
int want_affine = 0;
int sync = wake_flags & WF_SYNC;
- if (sd_flag & SD_BALANCE_WAKE)
- want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
+ if (sd_flag & SD_BALANCE_WAKE) {
+ record_wakee(p);
+ want_affine = !wake_wide(p, sibling_count_hint) &&
+ !wake_cap(p, cpu, prev_cpu) &&
+ cpumask_test_cpu(cpu, &p->cpus_allowed);
+ }
+
+ if (energy_aware() && !(cpu_rq(prev_cpu)->rd->overutilized))
+ return select_energy_cpu_brute(p, prev_cpu, sync);
rcu_read_lock();
for_each_domain(cpu, tmp) {
@@ -4993,47 +6836,25 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
if (affine_sd) {
sd = NULL; /* Prefer wake_affine over balance flags */
- if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
+ if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync))
new_cpu = cpu;
}
+ if (sd && !(sd_flag & SD_BALANCE_FORK)) {
+ /*
+ * We're going to need the task's util for capacity_spare_wake
+ * in find_idlest_group. Sync it up to prev_cpu's
+ * last_update_time.
+ */
+ sync_entity_load_avg(&p->se);
+ }
+
if (!sd) {
if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
- new_cpu = select_idle_sibling(p, new_cpu);
+ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
- } else while (sd) {
- struct sched_group *group;
- int weight;
-
- if (!(sd->flags & sd_flag)) {
- sd = sd->child;
- continue;
- }
-
- group = find_idlest_group(sd, p, cpu, sd_flag);
- if (!group) {
- sd = sd->child;
- continue;
- }
-
- new_cpu = find_idlest_cpu(group, p, cpu);
- if (new_cpu == -1 || new_cpu == cpu) {
- /* Now try balancing at a lower domain level of cpu */
- sd = sd->child;
- continue;
- }
-
- /* Now try balancing at a lower domain level of new_cpu */
- cpu = new_cpu;
- weight = sd->span_weight;
- sd = NULL;
- for_each_domain(cpu, tmp) {
- if (weight <= tmp->span_weight)
- break;
- if (tmp->flags & sd_flag)
- sd = tmp;
- }
- /* while loop will break here if sd == NULL */
+ } else {
+ new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
}
rcu_read_unlock();
@@ -5068,6 +6889,8 @@ static void task_dead_fair(struct task_struct *p)
{
remove_entity_load_avg(&p->se);
}
+#else
+#define task_fits_max(p, cpu) true
#endif /* CONFIG_SMP */
static unsigned long
@@ -5314,6 +7137,8 @@ again:
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
+ rq->misfit_task = !task_fits_max(p, rq->cpu);
+
return p;
simple:
cfs_rq = &rq->cfs;
@@ -5335,9 +7160,12 @@ simple:
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
+ rq->misfit_task = !task_fits_max(p, rq->cpu);
+
return p;
idle:
+ rq->misfit_task = 0;
/*
* This is OK, because current is on_cpu, which avoids it being picked
* for load-balance and preemption/IRQs are still disabled avoiding
@@ -5550,6 +7378,13 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
enum fbq_type { regular, remote, all };
+enum group_type {
+ group_other = 0,
+ group_misfit_task,
+ group_imbalanced,
+ group_overloaded,
+};
+
#define LBF_ALL_PINNED 0x01
#define LBF_NEED_BREAK 0x02
#define LBF_DST_PINNED 0x04
@@ -5568,6 +7403,7 @@ struct lb_env {
int new_dst_cpu;
enum cpu_idle_type idle;
long imbalance;
+ unsigned int src_grp_nr_running;
/* The set of CPUs under consideration for load-balancing */
struct cpumask *cpus;
@@ -5578,6 +7414,7 @@ struct lb_env {
unsigned int loop_max;
enum fbq_type fbq_type;
+ enum group_type busiest_group_type;
struct list_head tasks;
};
@@ -5759,7 +7596,9 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
deactivate_task(env->src_rq, p, 0);
p->on_rq = TASK_ON_RQ_MIGRATING;
+ double_lock_balance(env->src_rq, env->dst_rq);
set_task_cpu(p, env->dst_cpu);
+ double_unlock_balance(env->src_rq, env->dst_rq);
}
/*
@@ -5947,8 +7786,13 @@ static void update_blocked_averages(int cpu)
if (throttled_hierarchy(cfs_rq))
continue;
- if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq))
+ if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq,
+ true))
update_tg_load_avg(cfs_rq, 0);
+
+ /* Propagate pending load changes to the parent */
+ if (cfs_rq->tg->se[cpu])
+ update_load_avg(cfs_rq->tg->se[cpu], 0);
}
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -5968,10 +7812,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
if (cfs_rq->last_h_load_update == now)
return;
- cfs_rq->h_load_next = NULL;
+ WRITE_ONCE(cfs_rq->h_load_next, NULL);
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- cfs_rq->h_load_next = se;
+ WRITE_ONCE(cfs_rq->h_load_next, se);
if (cfs_rq->last_h_load_update == now)
break;
}
@@ -5981,7 +7825,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
cfs_rq->last_h_load_update = now;
}
- while ((se = cfs_rq->h_load_next) != NULL) {
+ while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
load = cfs_rq->h_load;
load = div64_ul(load * se->avg.load_avg,
cfs_rq_load_avg(cfs_rq) + 1);
@@ -6008,7 +7852,7 @@ static inline void update_blocked_averages(int cpu)
raw_spin_lock_irqsave(&rq->lock, flags);
update_rq_clock(rq);
- update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+ update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -6020,12 +7864,6 @@ static unsigned long task_h_load(struct task_struct *p)
/********** Helpers for find_busiest_group ************************/
-enum group_type {
- group_other = 0,
- group_imbalanced,
- group_overloaded,
-};
-
/*
* sg_lb_stats - stats of a sched_group required for load_balancing
*/
@@ -6041,6 +7879,7 @@ struct sg_lb_stats {
unsigned int group_weight;
enum group_type group_type;
int group_no_capacity;
+ int group_misfit_task; /* A cpu has a task too big for its capacity */
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
unsigned int nr_preferred_running;
@@ -6132,19 +7971,58 @@ static unsigned long scale_rt_capacity(int cpu)
used = div_u64(avg, total);
+ /*
+ * deadline bandwidth is defined at system level so we must
+ * weight this bandwidth with the max capacity of the system.
+ * As a reminder, avg_bw is 20bits width and
+ * scale_cpu_capacity is 10 bits width
+ */
+ used += div_u64(rq->dl.avg_bw, arch_scale_cpu_capacity(NULL, cpu));
+
if (likely(used < SCHED_CAPACITY_SCALE))
return SCHED_CAPACITY_SCALE - used;
return 1;
}
+void init_max_cpu_capacity(struct max_cpu_capacity *mcc)
+{
+ raw_spin_lock_init(&mcc->lock);
+ mcc->val = 0;
+ mcc->cpu = -1;
+}
+
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
{
unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
struct sched_group *sdg = sd->groups;
+ struct max_cpu_capacity *mcc;
+ unsigned long max_capacity;
+ int max_cap_cpu;
+ unsigned long flags;
cpu_rq(cpu)->cpu_capacity_orig = capacity;
+ mcc = &cpu_rq(cpu)->rd->max_cpu_capacity;
+
+ raw_spin_lock_irqsave(&mcc->lock, flags);
+ max_capacity = mcc->val;
+ max_cap_cpu = mcc->cpu;
+
+ if ((max_capacity > capacity && max_cap_cpu == cpu) ||
+ (max_capacity < capacity)) {
+ mcc->val = capacity;
+ mcc->cpu = cpu;
+#ifdef CONFIG_SCHED_DEBUG
+ raw_spin_unlock_irqrestore(&mcc->lock, flags);
+ printk_deferred(KERN_INFO "CPU%d: update max cpu_capacity %lu\n",
+ cpu, capacity);
+ goto skip_unlock;
+#endif
+ }
+ raw_spin_unlock_irqrestore(&mcc->lock, flags);
+
+skip_unlock: __attribute__ ((unused));
capacity *= scale_rt_capacity(cpu);
capacity >>= SCHED_CAPACITY_SHIFT;
@@ -6153,13 +8031,15 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
cpu_rq(cpu)->cpu_capacity = capacity;
sdg->sgc->capacity = capacity;
+ sdg->sgc->max_capacity = capacity;
+ sdg->sgc->min_capacity = capacity;
}
void update_group_capacity(struct sched_domain *sd, int cpu)
{
struct sched_domain *child = sd->child;
struct sched_group *group, *sdg = sd->groups;
- unsigned long capacity;
+ unsigned long capacity, max_capacity, min_capacity;
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
@@ -6172,6 +8052,8 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
}
capacity = 0;
+ max_capacity = 0;
+ min_capacity = ULONG_MAX;
if (child->flags & SD_OVERLAP) {
/*
@@ -6196,11 +8078,13 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
*/
if (unlikely(!rq->sd)) {
capacity += capacity_of(cpu);
- continue;
+ } else {
+ sgc = rq->sd->groups->sgc;
+ capacity += sgc->capacity;
}
- sgc = rq->sd->groups->sgc;
- capacity += sgc->capacity;
+ max_capacity = max(capacity, max_capacity);
+ min_capacity = min(capacity, min_capacity);
}
} else {
/*
@@ -6210,12 +8094,18 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
group = child->groups;
do {
- capacity += group->sgc->capacity;
+ struct sched_group_capacity *sgc = group->sgc;
+
+ capacity += sgc->capacity;
+ max_capacity = max(sgc->max_capacity, max_capacity);
+ min_capacity = min(sgc->min_capacity, min_capacity);
group = group->next;
} while (group != child->groups);
}
sdg->sgc->capacity = capacity;
+ sdg->sgc->max_capacity = max_capacity;
+ sdg->sgc->min_capacity = min_capacity;
}
/*
@@ -6310,6 +8200,18 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
return false;
}
+
+/*
+ * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller
+ * per-cpu capacity than sched_group ref.
+ */
+static inline bool
+group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref)
+{
+ return sg->sgc->max_capacity + capacity_margin - SCHED_LOAD_SCALE <
+ ref->sgc->max_capacity;
+}
+
static inline enum
group_type group_classify(struct sched_group *group,
struct sg_lb_stats *sgs)
@@ -6320,9 +8222,44 @@ group_type group_classify(struct sched_group *group,
if (sg_imbalanced(group))
return group_imbalanced;
+ if (sgs->group_misfit_task)
+ return group_misfit_task;
+
return group_other;
}
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * idle load balancing data
+ * - used by the nohz balance, but we want it available here
+ * so that we can see which CPUs have no tick.
+ */
+static struct {
+ cpumask_var_t idle_cpus_mask;
+ atomic_t nr_cpus;
+ unsigned long next_balance; /* in jiffy units */
+} nohz ____cacheline_aligned;
+
+static inline void update_cpu_stats_if_tickless(struct rq *rq)
+{
+ /* only called from update_sg_lb_stats when irqs are disabled */
+ if (cpumask_test_cpu(rq->cpu, nohz.idle_cpus_mask)) {
+ /* rate limit updates to once-per-jiffie at most */
+ if (READ_ONCE(jiffies) <= rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&rq->lock);
+ update_rq_clock(rq);
+ update_idle_cpu_load(rq);
+ update_cfs_rq_load_avg(rq->clock_task, &rq->cfs, false);
+ raw_spin_unlock(&rq->lock);
+ }
+}
+
+#else
+static inline void update_cpu_stats_if_tickless(struct rq *rq) { }
+#endif
+
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
* @env: The load balancing environment.
@@ -6331,20 +8268,27 @@ group_type group_classify(struct sched_group *group,
* @local_group: Does group contain this_cpu.
* @sgs: variable to hold the statistics for this group.
* @overload: Indicate more than one runnable task for any CPU.
+ * @overutilized: Indicate overutilization for any CPU.
*/
static inline void update_sg_lb_stats(struct lb_env *env,
struct sched_group *group, int load_idx,
int local_group, struct sg_lb_stats *sgs,
- bool *overload)
+ bool *overload, bool *overutilized)
{
unsigned long load;
- int i;
+ int i, nr_running;
memset(sgs, 0, sizeof(*sgs));
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
struct rq *rq = cpu_rq(i);
+ /* if we are entering idle and there are CPUs with
+ * their tick stopped, do an update for them
+ */
+ if (env->idle == CPU_NEWLY_IDLE)
+ update_cpu_stats_if_tickless(rq);
+
/* Bias balancing toward cpus of our domain */
if (local_group)
load = target_load(i, load_idx);
@@ -6355,7 +8299,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->group_util += cpu_util(i);
sgs->sum_nr_running += rq->cfs.h_nr_running;
- if (rq->nr_running > 1)
+ nr_running = rq->nr_running;
+ if (nr_running > 1)
*overload = true;
#ifdef CONFIG_NUMA_BALANCING
@@ -6363,8 +8308,17 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->nr_preferred_running += rq->nr_preferred_running;
#endif
sgs->sum_weighted_load += weighted_cpuload(i);
- if (idle_cpu(i))
+ /*
+ * No need to call idle_cpu() if nr_running is not 0
+ */
+ if (!nr_running && idle_cpu(i))
sgs->idle_cpus++;
+
+ if (cpu_overutilized(i)) {
+ *overutilized = true;
+ if (!sgs->group_misfit_task && rq->misfit_task)
+ sgs->group_misfit_task = capacity_of(i);
+ }
}
/* Adjust by relative CPU capacity of the group */
@@ -6406,9 +8360,31 @@ static bool update_sd_pick_busiest(struct lb_env *env,
if (sgs->group_type < busiest->group_type)
return false;
+ /*
+ * Candidate sg doesn't face any serious load-balance problems
+ * so don't pick it if the local sg is already filled up.
+ */
+ if (sgs->group_type == group_other &&
+ !group_has_capacity(env, &sds->local_stat))
+ return false;
+
if (sgs->avg_load <= busiest->avg_load)
return false;
+ if (!(env->sd->flags & SD_ASYM_CPUCAPACITY))
+ goto asym_packing;
+
+ /*
+ * Candidate sg has no more than one task per CPU and
+ * has higher per-CPU capacity. Migrating tasks to less
+ * capable CPUs may harm throughput. Maximize throughput,
+ * power/energy consequences are not considered.
+ */
+ if (sgs->sum_nr_running <= sgs->group_weight &&
+ group_smaller_cpu_capacity(sds->local, sg))
+ return false;
+
+asym_packing:
/* This is the busiest node in its class. */
if (!(env->sd->flags & SD_ASYM_PACKING))
return true;
@@ -6459,6 +8435,9 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq)
}
#endif /* CONFIG_NUMA_BALANCING */
+#define lb_sd_parent(sd) \
+ (sd->parent && sd->parent->groups != sd->parent->groups->next)
+
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @env: The load balancing environment.
@@ -6470,7 +8449,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats tmp_sgs;
int load_idx, prefer_sibling = 0;
- bool overload = false;
+ bool overload = false, overutilized = false;
if (child && child->flags & SD_PREFER_SIBLING)
prefer_sibling = 1;
@@ -6492,7 +8471,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
}
update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
- &overload);
+ &overload, &overutilized);
if (local_group)
goto next_group;
@@ -6514,6 +8493,15 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
sgs->group_type = group_classify(sg, sgs);
}
+ /*
+ * Ignore task groups with misfit tasks if local group has no
+ * capacity or if per-cpu capacity isn't higher.
+ */
+ if (sgs->group_type == group_misfit_task &&
+ (!group_has_capacity(env, &sds->local_stat) ||
+ !group_smaller_cpu_capacity(sg, sds->local)))
+ sgs->group_type = group_other;
+
if (update_sd_pick_busiest(env, sds, sg, sgs)) {
sds->busiest = sg;
sds->busiest_stat = *sgs;
@@ -6530,10 +8518,23 @@ next_group:
if (env->sd->flags & SD_NUMA)
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
- if (!env->sd->parent) {
+ env->src_grp_nr_running = sds->busiest_stat.sum_nr_running;
+
+ if (!lb_sd_parent(env->sd)) {
/* update overload indicator if we are at root domain */
if (env->dst_rq->rd->overload != overload)
env->dst_rq->rd->overload = overload;
+
+ /* Update over-utilization (tipping point, U >= 0) indicator */
+ if (env->dst_rq->rd->overutilized != overutilized) {
+ env->dst_rq->rd->overutilized = overutilized;
+ trace_sched_overutilized(overutilized);
+ }
+ } else {
+ if (!env->dst_rq->rd->overutilized && overutilized) {
+ env->dst_rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
}
}
@@ -6682,6 +8683,22 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
*/
if (busiest->avg_load <= sds->avg_load ||
local->avg_load >= sds->avg_load) {
+ /* Misfitting tasks should be migrated in any case */
+ if (busiest->group_type == group_misfit_task) {
+ env->imbalance = busiest->group_misfit_task;
+ return;
+ }
+
+ /*
+ * Busiest group is overloaded, local is not, use the spare
+ * cycles to maximize throughput
+ */
+ if (busiest->group_type == group_overloaded &&
+ local->group_type <= group_misfit_task) {
+ env->imbalance = busiest->load_per_task;
+ return;
+ }
+
env->imbalance = 0;
return fix_small_imbalance(env, sds);
}
@@ -6715,6 +8732,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
(sds->avg_load - local->avg_load) * local->group_capacity
) / SCHED_CAPACITY_SCALE;
+ /* Boost imbalance to allow misfit task to be balanced. */
+ if (busiest->group_type == group_misfit_task)
+ env->imbalance = max_t(long, env->imbalance,
+ busiest->group_misfit_task);
+
/*
* if *imbalance is less than the average load per runnable task
* there is no guarantee that any tasks will be moved so we'll have
@@ -6756,6 +8778,10 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
* this level.
*/
update_sd_lb_stats(env, &sds);
+
+ if (energy_aware() && !env->dst_rq->rd->overutilized)
+ goto out_balanced;
+
local = &sds.local_stat;
busiest = &sds.busiest_stat;
@@ -6779,11 +8805,19 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
if (busiest->group_type == group_imbalanced)
goto force_balance;
- /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
- if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
+ /*
+ * When dst_cpu is idle, prevent SMP nice and/or asymmetric group
+ * capacities from resulting in underutilization due to avg_load.
+ */
+ if (env->idle != CPU_NOT_IDLE && group_has_capacity(env, local) &&
busiest->group_no_capacity)
goto force_balance;
+ /* Misfitting tasks should be dealt with regardless of the avg load */
+ if (busiest->group_type == group_misfit_task) {
+ goto force_balance;
+ }
+
/*
* If the local group is busier than the selected busiest group
* don't try and pull any tasks.
@@ -6807,7 +8841,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
* might end up to just move the imbalance on another group
*/
if ((busiest->group_type != group_overloaded) &&
- (local->idle_cpus <= (busiest->idle_cpus + 1)))
+ (local->idle_cpus <= (busiest->idle_cpus + 1)) &&
+ !group_smaller_cpu_capacity(sds.busiest, sds.local))
goto out_balanced;
} else {
/*
@@ -6820,6 +8855,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
}
force_balance:
+ env->busiest_group_type = busiest->group_type;
/* Looks like there is an imbalance. Compute it */
calculate_imbalance(env, &sds);
return sds.busiest;
@@ -6878,7 +8914,8 @@ static struct rq *find_busiest_queue(struct lb_env *env,
*/
if (rq->nr_running == 1 && wl > env->imbalance &&
- !check_cpu_capacity(rq, env->sd))
+ !check_cpu_capacity(rq, env->sd) &&
+ env->busiest_group_type != group_misfit_task)
continue;
/*
@@ -6939,6 +8976,14 @@ static int need_active_balance(struct lb_env *env)
return 1;
}
+ if ((capacity_of(env->src_cpu) < capacity_of(env->dst_cpu)) &&
+ ((capacity_orig_of(env->src_cpu) < capacity_orig_of(env->dst_cpu))) &&
+ env->src_rq->cfs.h_nr_running == 1 &&
+ cpu_overutilized(env->src_cpu) &&
+ !cpu_overutilized(env->dst_cpu)) {
+ return 1;
+ }
+
return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
}
@@ -6987,7 +9032,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
int *continue_balancing)
{
int ld_moved, cur_ld_moved, active_balance = 0;
- struct sched_domain *sd_parent = sd->parent;
+ struct sched_domain *sd_parent = lb_sd_parent(sd) ? sd->parent : NULL;
struct sched_group *group;
struct rq *busiest;
unsigned long flags;
@@ -7054,6 +9099,7 @@ redo:
more_balance:
raw_spin_lock_irqsave(&busiest->lock, flags);
+ update_rq_clock(busiest);
/*
* cur_ld_moved - load moved in current iteration
@@ -7151,7 +9197,8 @@ more_balance:
* excessive cache_hot migrations and active balances.
*/
if (idle != CPU_NEWLY_IDLE)
- sd->nr_balance_failed++;
+ if (env.src_grp_nr_running > 1)
+ sd->nr_balance_failed++;
if (need_active_balance(&env)) {
raw_spin_lock_irqsave(&busiest->lock, flags);
@@ -7292,8 +9339,9 @@ static int idle_balance(struct rq *this_rq)
*/
this_rq->idle_stamp = rq_clock(this_rq);
- if (this_rq->avg_idle < sysctl_sched_migration_cost ||
- !this_rq->rd->overload) {
+ if (!energy_aware() &&
+ (this_rq->avg_idle < sysctl_sched_migration_cost ||
+ !this_rq->rd->overload)) {
rcu_read_lock();
sd = rcu_dereference_check_sched_domain(this_rq->sd);
if (sd)
@@ -7386,8 +9434,18 @@ static int active_load_balance_cpu_stop(void *data)
int busiest_cpu = cpu_of(busiest_rq);
int target_cpu = busiest_rq->push_cpu;
struct rq *target_rq = cpu_rq(target_cpu);
- struct sched_domain *sd;
+ struct sched_domain *sd = NULL;
struct task_struct *p = NULL;
+ struct task_struct *push_task = NULL;
+ int push_task_detached = 0;
+ struct lb_env env = {
+ .sd = sd,
+ .dst_cpu = target_cpu,
+ .dst_rq = target_rq,
+ .src_cpu = busiest_rq->cpu,
+ .src_rq = busiest_rq,
+ .idle = CPU_IDLE,
+ };
raw_spin_lock_irq(&busiest_rq->lock);
@@ -7407,6 +9465,17 @@ static int active_load_balance_cpu_stop(void *data)
*/
BUG_ON(busiest_rq == target_rq);
+ push_task = busiest_rq->push_task;
+ if (push_task) {
+ if (task_on_rq_queued(push_task) &&
+ task_cpu(push_task) == busiest_cpu &&
+ cpu_online(target_cpu)) {
+ detach_task(push_task, &env);
+ push_task_detached = 1;
+ }
+ goto out_unlock;
+ }
+
/* Search for an sd spanning us and the target CPU. */
rcu_read_lock();
for_each_domain(target_cpu, sd) {
@@ -7416,16 +9485,9 @@ static int active_load_balance_cpu_stop(void *data)
}
if (likely(sd)) {
- struct lb_env env = {
- .sd = sd,
- .dst_cpu = target_cpu,
- .dst_rq = target_rq,
- .src_cpu = busiest_rq->cpu,
- .src_rq = busiest_rq,
- .idle = CPU_IDLE,
- };
-
+ env.sd = sd;
schedstat_inc(sd, alb_count);
+ update_rq_clock(busiest_rq);
p = detach_one_task(&env);
if (p)
@@ -7436,8 +9498,18 @@ static int active_load_balance_cpu_stop(void *data)
rcu_read_unlock();
out_unlock:
busiest_rq->active_balance = 0;
+
+ if (push_task)
+ busiest_rq->push_task = NULL;
+
raw_spin_unlock(&busiest_rq->lock);
+ if (push_task) {
+ if (push_task_detached)
+ attach_one_task(target_rq, push_task);
+ put_task_struct(push_task);
+ }
+
if (p)
attach_one_task(target_rq, p);
@@ -7458,12 +9530,6 @@ static inline int on_null_domain(struct rq *rq)
* needed, they will kick the idle load balancer, which then does idle
* load balancing for all the idle CPUs.
*/
-static struct {
- cpumask_var_t idle_cpus_mask;
- atomic_t nr_cpus;
- unsigned long next_balance; /* in jiffy units */
-} nohz ____cacheline_aligned;
-
static inline int find_new_ilb(void)
{
int ilb = cpumask_first(nohz.idle_cpus_mask);
@@ -7809,9 +9875,14 @@ static inline bool nohz_kick_needed(struct rq *rq)
if (time_before(now, nohz.next_balance))
return false;
- if (rq->nr_running >= 2)
+ if (rq->nr_running >= 2 &&
+ (!energy_aware() || cpu_overutilized(cpu)))
return true;
+ /* Do idle load balance if there have misfit task */
+ if (energy_aware())
+ return rq->misfit_task;
+
rcu_read_lock();
sd = rcu_dereference(per_cpu(sd_busy, cpu));
if (sd) {
@@ -7903,6 +9974,47 @@ static void rq_offline_fair(struct rq *rq)
unthrottle_offline_cfs_rqs(rq);
}
+static inline int
+kick_active_balance(struct rq *rq, struct task_struct *p, int new_cpu)
+{
+ int rc = 0;
+
+ /* Invoke active balance to force migrate currently running task */
+ raw_spin_lock(&rq->lock);
+ if (!rq->active_balance) {
+ rq->active_balance = 1;
+ rq->push_cpu = new_cpu;
+ get_task_struct(p);
+ rq->push_task = p;
+ rc = 1;
+ }
+ raw_spin_unlock(&rq->lock);
+
+ return rc;
+}
+
+void check_for_migration(struct rq *rq, struct task_struct *p)
+{
+ int new_cpu;
+ int active_balance;
+ int cpu = task_cpu(p);
+
+ if (energy_aware() && rq->misfit_task) {
+ if (rq->curr->state != TASK_RUNNING ||
+ rq->curr->nr_cpus_allowed == 1)
+ return;
+
+ new_cpu = select_energy_cpu_brute(p, cpu, 0);
+ if (capacity_orig_of(new_cpu) > capacity_orig_of(cpu)) {
+ active_balance = kick_active_balance(rq, p, new_cpu);
+ if (active_balance)
+ stop_one_cpu_nowait(cpu,
+ active_load_balance_cpu_stop,
+ rq, &rq->active_balance_work);
+ }
+ }
+}
+
#endif /* CONFIG_SMP */
/*
@@ -7920,6 +10032,16 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
+
+#ifdef CONFIG_SMP
+ if (!rq->rd->overutilized && cpu_overutilized(task_cpu(curr))) {
+ rq->rd->overutilized = true;
+ trace_sched_overutilized(true);
+ }
+
+ rq->misfit_task = !task_fits_max(curr, rq->cpu);
+#endif
+
}
/*
@@ -7931,31 +10053,17 @@ static void task_fork_fair(struct task_struct *p)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se, *curr;
- int this_cpu = smp_processor_id();
struct rq *rq = this_rq();
- unsigned long flags;
-
- raw_spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock(&rq->lock);
update_rq_clock(rq);
cfs_rq = task_cfs_rq(current);
curr = cfs_rq->curr;
-
- /*
- * Not only the cpu but also the task_group of the parent might have
- * been changed after parent->se.parent,cfs_rq were copied to
- * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
- * of child point to valid ones.
- */
- rcu_read_lock();
- __set_task_cpu(p, this_cpu);
- rcu_read_unlock();
-
- update_curr(cfs_rq);
-
- if (curr)
+ if (curr) {
+ update_curr(cfs_rq);
se->vruntime = curr->vruntime;
+ }
place_entity(cfs_rq, se, 1);
if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
@@ -7968,8 +10076,7 @@ static void task_fork_fair(struct task_struct *p)
}
se->vruntime -= cfs_rq->min_vruntime;
-
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock(&rq->lock);
}
/*
@@ -8021,6 +10128,61 @@ static inline bool vruntime_normalized(struct task_struct *p)
return false;
}
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * Propagate the changes of the sched_entity across the tg tree to make it
+ * visible to the root
+ */
+static void propagate_entity_cfs_rq(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq;
+
+ /* Start to propagate at parent */
+ se = se->parent;
+
+ for_each_sched_entity(se) {
+ cfs_rq = cfs_rq_of(se);
+
+ if (cfs_rq_throttled(cfs_rq))
+ break;
+
+ update_load_avg(se, UPDATE_TG);
+ }
+}
+#else
+static void propagate_entity_cfs_rq(struct sched_entity *se) { }
+#endif
+
+static void detach_entity_cfs_rq(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /* Catch up with the cfs_rq and remove our load when we leave */
+ update_load_avg(se, 0);
+ detach_entity_load_avg(cfs_rq, se);
+ update_tg_load_avg(cfs_rq, false);
+ propagate_entity_cfs_rq(se);
+}
+
+static void attach_entity_cfs_rq(struct sched_entity *se)
+{
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ /*
+ * Since the real-depth could have been changed (only FAIR
+ * class maintain depth value), reset depth properly.
+ */
+ se->depth = se->parent ? se->parent->depth + 1 : 0;
+#endif
+
+ /* Synchronize entity with its cfs_rq */
+ update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD);
+ attach_entity_load_avg(cfs_rq, se);
+ update_tg_load_avg(cfs_rq, false);
+ propagate_entity_cfs_rq(se);
+}
+
static void detach_task_cfs_rq(struct task_struct *p)
{
struct sched_entity *se = &p->se;
@@ -8035,8 +10197,7 @@ static void detach_task_cfs_rq(struct task_struct *p)
se->vruntime -= cfs_rq->min_vruntime;
}
- /* Catch up with the cfs_rq and remove our load when we leave */
- detach_entity_load_avg(cfs_rq, se);
+ detach_entity_cfs_rq(se);
}
static void attach_task_cfs_rq(struct task_struct *p)
@@ -8044,16 +10205,7 @@ static void attach_task_cfs_rq(struct task_struct *p)
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
-#ifdef CONFIG_FAIR_GROUP_SCHED
- /*
- * Since the real-depth could have been changed (only FAIR
- * class maintain depth value), reset depth properly.
- */
- se->depth = se->parent ? se->parent->depth + 1 : 0;
-#endif
-
- /* Synchronize task with its cfs_rq */
- attach_entity_load_avg(cfs_rq, se);
+ attach_entity_cfs_rq(se);
if (!vruntime_normalized(p))
se->vruntime += cfs_rq->min_vruntime;
@@ -8107,12 +10259,23 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
#endif
#ifdef CONFIG_SMP
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ cfs_rq->propagate_avg = 0;
+#endif
atomic_long_set(&cfs_rq->removed_load_avg, 0);
atomic_long_set(&cfs_rq->removed_util_avg, 0);
#endif
}
#ifdef CONFIG_FAIR_GROUP_SCHED
+static void task_set_group_fair(struct task_struct *p)
+{
+ struct sched_entity *se = &p->se;
+
+ set_task_rq(p, task_cpu(p));
+ se->depth = se->parent ? se->parent->depth + 1 : 0;
+}
+
static void task_move_group_fair(struct task_struct *p)
{
detach_task_cfs_rq(p);
@@ -8125,6 +10288,19 @@ static void task_move_group_fair(struct task_struct *p)
attach_task_cfs_rq(p);
}
+static void task_change_group_fair(struct task_struct *p, int type)
+{
+ switch (type) {
+ case TASK_SET_GROUP:
+ task_set_group_fair(p);
+ break;
+
+ case TASK_MOVE_GROUP:
+ task_move_group_fair(p);
+ break;
+ }
+}
+
void free_fair_sched_group(struct task_group *tg)
{
int i;
@@ -8134,11 +10310,8 @@ void free_fair_sched_group(struct task_group *tg)
for_each_possible_cpu(i) {
if (tg->cfs_rq)
kfree(tg->cfs_rq[i]);
- if (tg->se) {
- if (tg->se[i])
- remove_entity_load_avg(tg->se[i]);
+ if (tg->se)
kfree(tg->se[i]);
- }
}
kfree(tg->cfs_rq);
@@ -8147,8 +10320,9 @@ void free_fair_sched_group(struct task_group *tg)
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
- struct cfs_rq *cfs_rq;
struct sched_entity *se;
+ struct cfs_rq *cfs_rq;
+ struct rq *rq;
int i;
tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
@@ -8163,6 +10337,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
init_cfs_bandwidth(tg_cfs_bandwidth(tg));
for_each_possible_cpu(i) {
+ rq = cpu_rq(i);
+
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
GFP_KERNEL, cpu_to_node(i));
if (!cfs_rq)
@@ -8176,6 +10352,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
init_cfs_rq(cfs_rq);
init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
init_entity_runnable_average(se);
+
+ raw_spin_lock_irq(&rq->lock);
+ post_init_entity_util_avg(se);
+ raw_spin_unlock_irq(&rq->lock);
}
return 1;
@@ -8186,21 +10366,29 @@ err:
return 0;
}
-void unregister_fair_sched_group(struct task_group *tg, int cpu)
+void unregister_fair_sched_group(struct task_group *tg)
{
- struct rq *rq = cpu_rq(cpu);
unsigned long flags;
+ struct rq *rq;
+ int cpu;
- /*
- * Only empty task groups can be destroyed; so we can speculatively
- * check on_list without danger of it being re-added.
- */
- if (!tg->cfs_rq[cpu]->on_list)
- return;
+ for_each_possible_cpu(cpu) {
+ if (tg->se[cpu])
+ remove_entity_load_avg(tg->se[cpu]);
- raw_spin_lock_irqsave(&rq->lock, flags);
- list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ /*
+ * Only empty task groups can be destroyed; so we can speculatively
+ * check on_list without danger of it being re-added.
+ */
+ if (!tg->cfs_rq[cpu]->on_list)
+ continue;
+
+ rq = cpu_rq(cpu);
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+ }
}
void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
@@ -8264,8 +10452,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
/* Possible calls to update_curr() need rq clock */
update_rq_clock(rq);
- for_each_sched_entity(se)
- update_cfs_shares(group_cfs_rq(se));
+ for_each_sched_entity(se) {
+ update_load_avg(se, UPDATE_TG);
+ update_cfs_shares(se);
+ }
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -8282,7 +10472,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
return 1;
}
-void unregister_fair_sched_group(struct task_group *tg, int cpu) { }
+void unregister_fair_sched_group(struct task_group *tg) { }
#endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -8342,7 +10532,7 @@ const struct sched_class fair_sched_class = {
.update_curr = update_curr_fair,
#ifdef CONFIG_FAIR_GROUP_SCHED
- .task_move_group = task_move_group_fair,
+ .task_change_group = task_change_group_fair,
#endif
};
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 69631fa46c2f..55e461055332 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -69,3 +69,12 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true)
SCHED_FEAT(LB_MIN, false)
SCHED_FEAT(ATTACH_AGE_LOAD, true)
+/*
+ * Energy aware scheduling. Use platform energy model to guide scheduling
+ * decisions optimizing for energy efficiency.
+ */
+#ifdef CONFIG_DEFAULT_USE_ENERGY_AWARE
+SCHED_FEAT(ENERGY_AWARE, true)
+#else
+SCHED_FEAT(ENERGY_AWARE, false)
+#endif
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 4a2ef5a02fd3..cc0975f94a8d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -19,9 +19,10 @@
* sched_idle_set_state - Record idle state for the current CPU.
* @idle_state: State to record.
*/
-void sched_idle_set_state(struct cpuidle_state *idle_state)
+void sched_idle_set_state(struct cpuidle_state *idle_state, int index)
{
idle_set_state(this_rq(), idle_state);
+ idle_set_state_idx(this_rq(), index);
}
static int __read_mostly cpu_idle_force_poll;
@@ -132,7 +133,7 @@ static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
*/
static void cpuidle_idle_call(void)
{
- struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+ struct cpuidle_device *dev = cpuidle_get_device();
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int next_state, entered_state;
@@ -219,6 +220,7 @@ static void cpu_idle_loop(void)
*/
__current_set_polling();
+ quiet_vmstat();
tick_nohz_idle_enter();
while (!need_resched()) {
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index c4ae0f1fdf9b..33d7003fa1b8 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -9,7 +9,8 @@
#ifdef CONFIG_SMP
static int
-select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags,
+ int sibling_count_hint)
{
return task_cpu(p); /* IDLE tasks as never migrated */
}
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index b0b93fd33af9..f8e8d68ed3fd 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -201,8 +201,9 @@ void calc_load_exit_idle(void)
struct rq *this_rq = this_rq();
/*
- * If we're still before the sample window, we're done.
+ * If we're still before the pending sample window, we're done.
*/
+ this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update))
return;
@@ -211,7 +212,6 @@ void calc_load_exit_idle(void)
* accounted through the nohz accounting, so skip the entire deal and
* sync up for the next window.
*/
- this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update + 10))
this_rq->calc_load_update += LOAD_FREQ;
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8ec86abe0ea1..4184d4a97fd2 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -7,6 +7,10 @@
#include <linux/slab.h>
#include <linux/irq_work.h>
+#include <linux/hrtimer.h>
+
+#include "walt.h"
+#include "tune.h"
int sched_rr_timeslice = RR_TIMESLICE;
@@ -64,10 +68,6 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
raw_spin_unlock(&rt_b->rt_runtime_lock);
}
-#if defined(CONFIG_SMP) && defined(HAVE_RT_PUSH_IPI)
-static void push_irq_work_func(struct irq_work *work);
-#endif
-
void init_rt_rq(struct rt_rq *rt_rq)
{
struct rt_prio_array *array;
@@ -87,13 +87,6 @@ void init_rt_rq(struct rt_rq *rt_rq)
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
plist_head_init(&rt_rq->pushable_tasks);
-
-#ifdef HAVE_RT_PUSH_IPI
- rt_rq->push_flags = 0;
- rt_rq->push_cpu = nr_cpu_ids;
- raw_spin_lock_init(&rt_rq->push_lock);
- init_irq_work(&rt_rq->push_work, push_irq_work_func);
-#endif
#endif /* CONFIG_SMP */
/* We start is dequeued state, because no RT tasks are queued */
rt_rq->rt_queued = 0;
@@ -833,6 +826,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
struct rq *rq = rq_of_rt_rq(rt_rq);
raw_spin_lock(&rq->lock);
+ update_rq_clock(rq);
+
if (rt_rq->rt_time) {
u64 runtime;
@@ -889,6 +884,51 @@ static inline int rt_se_prio(struct sched_rt_entity *rt_se)
return rt_task_of(rt_se)->prio;
}
+static void dump_throttled_rt_tasks(struct rt_rq *rt_rq)
+{
+ struct rt_prio_array *array = &rt_rq->active;
+ struct sched_rt_entity *rt_se;
+ char buf[500];
+ char *pos = buf;
+ char *end = buf + sizeof(buf);
+ int idx;
+
+ pos += snprintf(pos, sizeof(buf),
+ "sched: RT throttling activated for rt_rq %p (cpu %d)\n",
+ rt_rq, cpu_of(rq_of_rt_rq(rt_rq)));
+
+ if (bitmap_empty(array->bitmap, MAX_RT_PRIO))
+ goto out;
+
+ pos += snprintf(pos, end - pos, "potential CPU hogs:\n");
+ idx = sched_find_first_bit(array->bitmap);
+ while (idx < MAX_RT_PRIO) {
+ list_for_each_entry(rt_se, array->queue + idx, run_list) {
+ struct task_struct *p;
+
+ if (!rt_entity_is_task(rt_se))
+ continue;
+
+ p = rt_task_of(rt_se);
+ if (pos < end)
+ pos += snprintf(pos, end - pos, "\t%s (%d)\n",
+ p->comm, p->pid);
+ }
+ idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx + 1);
+ }
+out:
+#ifdef CONFIG_PANIC_ON_RT_THROTTLING
+ /*
+ * Use pr_err() in the BUG() case since printk_sched() will
+ * not get flushed and deadlock is not a concern.
+ */
+ pr_err("%s", buf);
+ BUG();
+#else
+ printk_deferred("%s", buf);
+#endif
+}
+
static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
{
u64 runtime = sched_rt_runtime(rt_rq);
@@ -912,8 +952,14 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
* but accrue some time due to boosting.
*/
if (likely(rt_b->rt_runtime)) {
+ static bool once = false;
+
rt_rq->rt_throttled = 1;
- printk_deferred_once("sched: RT throttling activated\n");
+
+ if (!once) {
+ once = true;
+ dump_throttled_rt_tasks(rt_rq);
+ }
} else {
/*
* In case we did anyway, make it go away,
@@ -932,6 +978,70 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
return 0;
}
+#define RT_SCHEDTUNE_INTERVAL 50000000ULL
+
+static enum hrtimer_restart rt_schedtune_timer(struct hrtimer *timer)
+{
+ struct sched_rt_entity *rt_se = container_of(timer,
+ struct sched_rt_entity,
+ schedtune_timer);
+ struct task_struct *p = rt_task_of(rt_se);
+ struct rq *rq = task_rq(p);
+
+ raw_spin_lock(&rq->lock);
+
+ /*
+ * Nothing to do if:
+ * - task has switched runqueues
+ * - task isn't RT anymore
+ */
+ if (rq != task_rq(p) || (p->sched_class != &rt_sched_class))
+ goto out;
+
+ /*
+ * If task got enqueued back during callback time, it means we raced
+ * with the enqueue on another cpu, that's Ok, just do nothing as
+ * enqueue path would have tried to cancel us and we shouldn't run
+ * Also check the schedtune_enqueued flag as class-switch on a
+ * sleeping task may have already canceled the timer and done dq
+ */
+ if (p->on_rq || !rt_se->schedtune_enqueued)
+ goto out;
+
+ /*
+ * RT task is no longer active, cancel boost
+ */
+ rt_se->schedtune_enqueued = false;
+ schedtune_dequeue_task(p, cpu_of(rq));
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
+out:
+ raw_spin_unlock(&rq->lock);
+
+ /*
+ * This can free the task_struct if no more references.
+ */
+ put_task_struct(p);
+
+ return HRTIMER_NORESTART;
+}
+
+void init_rt_schedtune_timer(struct sched_rt_entity *rt_se)
+{
+ struct hrtimer *timer = &rt_se->schedtune_timer;
+
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ timer->function = rt_schedtune_timer;
+ rt_se->schedtune_enqueued = false;
+}
+
+static void start_schedtune_timer(struct sched_rt_entity *rt_se)
+{
+ struct hrtimer *timer = &rt_se->schedtune_timer;
+
+ hrtimer_start(timer, ns_to_ktime(RT_SCHEDTUNE_INTERVAL),
+ HRTIMER_MODE_REL_PINNED);
+}
+
/*
* Update the current task's runtime statistics. Skip current tasks that
* are not in our scheduling class.
@@ -949,6 +1059,9 @@ static void update_curr_rt(struct rq *rq)
if (unlikely((s64)delta_exec <= 0))
return;
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
+
schedstat_set(curr->se.statistics.exec_max,
max(curr->se.statistics.exec_max, delta_exec));
@@ -1261,9 +1374,37 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
rt_se->timeout = 0;
enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
+ walt_inc_cumulative_runnable_avg(rq, p);
if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
+
+ if (!schedtune_task_boost(p))
+ return;
+
+ /*
+ * If schedtune timer is active, that means a boost was already
+ * done, just cancel the timer so that deboost doesn't happen.
+ * Otherwise, increase the boost. If an enqueued timer was
+ * cancelled, put the task reference.
+ */
+ if (hrtimer_try_to_cancel(&rt_se->schedtune_timer) == 1)
+ put_task_struct(p);
+
+ /*
+ * schedtune_enqueued can be true in the following situation:
+ * enqueue_task_rt grabs rq lock before timer fires
+ * or before its callback acquires rq lock
+ * schedtune_enqueued can be false if timer callback is running
+ * and timer just released rq lock, or if the timer finished
+ * running and canceling the boost
+ */
+ if (rt_se->schedtune_enqueued)
+ return;
+
+ rt_se->schedtune_enqueued = true;
+ schedtune_enqueue_task(p, cpu_of(rq));
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
}
static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -1272,8 +1413,22 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
update_curr_rt(rq);
dequeue_rt_entity(rt_se);
+ walt_dec_cumulative_runnable_avg(rq, p);
dequeue_pushable_task(rq, p);
+
+ if (!rt_se->schedtune_enqueued)
+ return;
+
+ if (flags == DEQUEUE_SLEEP) {
+ get_task_struct(p);
+ start_schedtune_timer(rt_se);
+ return;
+ }
+
+ rt_se->schedtune_enqueued = false;
+ schedtune_dequeue_task(p, cpu_of(rq));
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
}
/*
@@ -1313,8 +1468,35 @@ static void yield_task_rt(struct rq *rq)
#ifdef CONFIG_SMP
static int find_lowest_rq(struct task_struct *task);
+/*
+ * Perform a schedtune dequeue and cancelation of boost timers if needed.
+ * Should be called only with the rq->lock held.
+ */
+static void schedtune_dequeue_rt(struct rq *rq, struct task_struct *p)
+{
+ struct sched_rt_entity *rt_se = &p->rt;
+
+ BUG_ON(!raw_spin_is_locked(&rq->lock));
+
+ if (!rt_se->schedtune_enqueued)
+ return;
+
+ /*
+ * Incase of class change cancel any active timers. If an enqueued
+ * timer was cancelled, put the task ref.
+ */
+ if (hrtimer_try_to_cancel(&rt_se->schedtune_timer) == 1)
+ put_task_struct(p);
+
+ /* schedtune_enqueued is true, deboost it */
+ rt_se->schedtune_enqueued = false;
+ schedtune_dequeue_task(p, task_cpu(p));
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_RT);
+}
+
static int
-select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags,
+ int sibling_count_hint)
{
struct task_struct *curr;
struct rq *rq;
@@ -1366,6 +1548,19 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
rcu_read_unlock();
out:
+ /*
+ * If previous CPU was different, make sure to cancel any active
+ * schedtune timers and deboost.
+ */
+ if (task_cpu(p) != cpu) {
+ unsigned long fl;
+ struct rq *prq = task_rq(p);
+
+ raw_spin_lock_irqsave(&prq->lock, fl);
+ schedtune_dequeue_rt(prq, p);
+ raw_spin_unlock_irqrestore(&prq->lock, fl);
+ }
+
return cpu;
}
@@ -1780,7 +1975,9 @@ retry:
}
deactivate_task(rq, next_task, 0);
+ next_task->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(next_task, lowest_rq->cpu);
+ next_task->on_rq = TASK_ON_RQ_QUEUED;
activate_task(lowest_rq, next_task, 0);
ret = 1;
@@ -1802,160 +1999,172 @@ static void push_rt_tasks(struct rq *rq)
}
#ifdef HAVE_RT_PUSH_IPI
+
/*
- * The search for the next cpu always starts at rq->cpu and ends
- * when we reach rq->cpu again. It will never return rq->cpu.
- * This returns the next cpu to check, or nr_cpu_ids if the loop
- * is complete.
+ * When a high priority task schedules out from a CPU and a lower priority
+ * task is scheduled in, a check is made to see if there's any RT tasks
+ * on other CPUs that are waiting to run because a higher priority RT task
+ * is currently running on its CPU. In this case, the CPU with multiple RT
+ * tasks queued on it (overloaded) needs to be notified that a CPU has opened
+ * up that may be able to run one of its non-running queued RT tasks.
+ *
+ * All CPUs with overloaded RT tasks need to be notified as there is currently
+ * no way to know which of these CPUs have the highest priority task waiting
+ * to run. Instead of trying to take a spinlock on each of these CPUs,
+ * which has shown to cause large latency when done on machines with many
+ * CPUs, sending an IPI to the CPUs to have them push off the overloaded
+ * RT tasks waiting to run.
+ *
+ * Just sending an IPI to each of the CPUs is also an issue, as on large
+ * count CPU machines, this can cause an IPI storm on a CPU, especially
+ * if its the only CPU with multiple RT tasks queued, and a large number
+ * of CPUs scheduling a lower priority task at the same time.
+ *
+ * Each root domain has its own irq work function that can iterate over
+ * all CPUs with RT overloaded tasks. Since all CPUs with overloaded RT
+ * tassk must be checked if there's one or many CPUs that are lowering
+ * their priority, there's a single irq work iterator that will try to
+ * push off RT tasks that are waiting to run.
+ *
+ * When a CPU schedules a lower priority task, it will kick off the
+ * irq work iterator that will jump to each CPU with overloaded RT tasks.
+ * As it only takes the first CPU that schedules a lower priority task
+ * to start the process, the rto_start variable is incremented and if
+ * the atomic result is one, then that CPU will try to take the rto_lock.
+ * This prevents high contention on the lock as the process handles all
+ * CPUs scheduling lower priority tasks.
+ *
+ * All CPUs that are scheduling a lower priority task will increment the
+ * rt_loop_next variable. This will make sure that the irq work iterator
+ * checks all RT overloaded CPUs whenever a CPU schedules a new lower
+ * priority task, even if the iterator is in the middle of a scan. Incrementing
+ * the rt_loop_next will cause the iterator to perform another scan.
*
- * rq->rt.push_cpu holds the last cpu returned by this function,
- * or if this is the first instance, it must hold rq->cpu.
*/
-static int rto_next_cpu(struct rq *rq)
+static int rto_next_cpu(struct root_domain *rd)
{
- int prev_cpu = rq->rt.push_cpu;
+ int next;
int cpu;
- cpu = cpumask_next(prev_cpu, rq->rd->rto_mask);
-
/*
- * If the previous cpu is less than the rq's CPU, then it already
- * passed the end of the mask, and has started from the beginning.
- * We end if the next CPU is greater or equal to rq's CPU.
+ * When starting the IPI RT pushing, the rto_cpu is set to -1,
+ * rt_next_cpu() will simply return the first CPU found in
+ * the rto_mask.
+ *
+ * If rto_next_cpu() is called with rto_cpu is a valid cpu, it
+ * will return the next CPU found in the rto_mask.
+ *
+ * If there are no more CPUs left in the rto_mask, then a check is made
+ * against rto_loop and rto_loop_next. rto_loop is only updated with
+ * the rto_lock held, but any CPU may increment the rto_loop_next
+ * without any locking.
*/
- if (prev_cpu < rq->cpu) {
- if (cpu >= rq->cpu)
- return nr_cpu_ids;
+ for (;;) {
- } else if (cpu >= nr_cpu_ids) {
- /*
- * We passed the end of the mask, start at the beginning.
- * If the result is greater or equal to the rq's CPU, then
- * the loop is finished.
- */
- cpu = cpumask_first(rq->rd->rto_mask);
- if (cpu >= rq->cpu)
- return nr_cpu_ids;
- }
- rq->rt.push_cpu = cpu;
+ /* When rto_cpu is -1 this acts like cpumask_first() */
+ cpu = cpumask_next(rd->rto_cpu, rd->rto_mask);
- /* Return cpu to let the caller know if the loop is finished or not */
- return cpu;
-}
+ rd->rto_cpu = cpu;
-static int find_next_push_cpu(struct rq *rq)
-{
- struct rq *next_rq;
- int cpu;
+ if (cpu < nr_cpu_ids)
+ return cpu;
- while (1) {
- cpu = rto_next_cpu(rq);
- if (cpu >= nr_cpu_ids)
- break;
- next_rq = cpu_rq(cpu);
+ rd->rto_cpu = -1;
- /* Make sure the next rq can push to this rq */
- if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr)
+ /*
+ * ACQUIRE ensures we see the @rto_mask changes
+ * made prior to the @next value observed.
+ *
+ * Matches WMB in rt_set_overload().
+ */
+ next = atomic_read_acquire(&rd->rto_loop_next);
+
+ if (rd->rto_loop == next)
break;
+
+ rd->rto_loop = next;
}
- return cpu;
+ return -1;
}
-#define RT_PUSH_IPI_EXECUTING 1
-#define RT_PUSH_IPI_RESTART 2
+static inline bool rto_start_trylock(atomic_t *v)
+{
+ return !atomic_cmpxchg_acquire(v, 0, 1);
+}
-static void tell_cpu_to_push(struct rq *rq)
+static inline void rto_start_unlock(atomic_t *v)
{
- int cpu;
+ atomic_set_release(v, 0);
+}
- if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
- raw_spin_lock(&rq->rt.push_lock);
- /* Make sure it's still executing */
- if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
- /*
- * Tell the IPI to restart the loop as things have
- * changed since it started.
- */
- rq->rt.push_flags |= RT_PUSH_IPI_RESTART;
- raw_spin_unlock(&rq->rt.push_lock);
- return;
- }
- raw_spin_unlock(&rq->rt.push_lock);
- }
+static void tell_cpu_to_push(struct rq *rq)
+{
+ int cpu = -1;
- /* When here, there's no IPI going around */
+ /* Keep the loop going if the IPI is currently active */
+ atomic_inc(&rq->rd->rto_loop_next);
- rq->rt.push_cpu = rq->cpu;
- cpu = find_next_push_cpu(rq);
- if (cpu >= nr_cpu_ids)
+ /* Only one CPU can initiate a loop at a time */
+ if (!rto_start_trylock(&rq->rd->rto_loop_start))
return;
- rq->rt.push_flags = RT_PUSH_IPI_EXECUTING;
+ raw_spin_lock(&rq->rd->rto_lock);
+
+ /*
+ * The rto_cpu is updated under the lock, if it has a valid cpu
+ * then the IPI is still running and will continue due to the
+ * update to loop_next, and nothing needs to be done here.
+ * Otherwise it is finishing up and an ipi needs to be sent.
+ */
+ if (rq->rd->rto_cpu < 0)
+ cpu = rto_next_cpu(rq->rd);
+
+ raw_spin_unlock(&rq->rd->rto_lock);
- irq_work_queue_on(&rq->rt.push_work, cpu);
+ rto_start_unlock(&rq->rd->rto_loop_start);
+
+ if (cpu >= 0) {
+ /* Make sure the rd does not get freed while pushing */
+ sched_get_rd(rq->rd);
+ irq_work_queue_on(&rq->rd->rto_push_work, cpu);
+ }
}
/* Called from hardirq context */
-static void try_to_push_tasks(void *arg)
+void rto_push_irq_work_func(struct irq_work *work)
{
- struct rt_rq *rt_rq = arg;
- struct rq *rq, *src_rq;
- int this_cpu;
+ struct root_domain *rd =
+ container_of(work, struct root_domain, rto_push_work);
+ struct rq *rq;
int cpu;
- this_cpu = rt_rq->push_cpu;
-
- /* Paranoid check */
- BUG_ON(this_cpu != smp_processor_id());
-
- rq = cpu_rq(this_cpu);
- src_rq = rq_of_rt_rq(rt_rq);
+ rq = this_rq();
-again:
+ /*
+ * We do not need to grab the lock to check for has_pushable_tasks.
+ * When it gets updated, a check is made if a push is possible.
+ */
if (has_pushable_tasks(rq)) {
raw_spin_lock(&rq->lock);
- push_rt_task(rq);
+ push_rt_tasks(rq);
raw_spin_unlock(&rq->lock);
}
- /* Pass the IPI to the next rt overloaded queue */
- raw_spin_lock(&rt_rq->push_lock);
- /*
- * If the source queue changed since the IPI went out,
- * we need to restart the search from that CPU again.
- */
- if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) {
- rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART;
- rt_rq->push_cpu = src_rq->cpu;
- }
+ raw_spin_lock(&rd->rto_lock);
- cpu = find_next_push_cpu(src_rq);
+ /* Pass the IPI to the next rt overloaded queue */
+ cpu = rto_next_cpu(rd);
- if (cpu >= nr_cpu_ids)
- rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING;
- raw_spin_unlock(&rt_rq->push_lock);
+ raw_spin_unlock(&rd->rto_lock);
- if (cpu >= nr_cpu_ids)
+ if (cpu < 0) {
+ sched_put_rd(rd);
return;
-
- /*
- * It is possible that a restart caused this CPU to be
- * chosen again. Don't bother with an IPI, just see if we
- * have more to push.
- */
- if (unlikely(cpu == rq->cpu))
- goto again;
+ }
/* Try the next RT overloaded CPU */
- irq_work_queue_on(&rt_rq->push_work, cpu);
-}
-
-static void push_irq_work_func(struct irq_work *work)
-{
- struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work);
-
- try_to_push_tasks(rt_rq);
+ irq_work_queue_on(&rd->rto_push_work, cpu);
}
#endif /* HAVE_RT_PUSH_IPI */
@@ -1965,8 +2174,9 @@ static void pull_rt_task(struct rq *this_rq)
bool resched = false;
struct task_struct *p;
struct rq *src_rq;
+ int rt_overload_count = rt_overloaded(this_rq);
- if (likely(!rt_overloaded(this_rq)))
+ if (likely(!rt_overload_count))
return;
/*
@@ -1975,6 +2185,11 @@ static void pull_rt_task(struct rq *this_rq)
*/
smp_rmb();
+ /* If we are the only overloaded CPU do nothing */
+ if (rt_overload_count == 1 &&
+ cpumask_test_cpu(this_rq->cpu, this_rq->rd->rto_mask))
+ return;
+
#ifdef HAVE_RT_PUSH_IPI
if (sched_feat(RT_PUSH_IPI)) {
tell_cpu_to_push(this_rq);
@@ -2034,7 +2249,9 @@ static void pull_rt_task(struct rq *this_rq)
resched = true;
deactivate_task(src_rq, p, 0);
+ p->on_rq = TASK_ON_RQ_MIGRATING;
set_task_cpu(p, this_cpu);
+ p->on_rq = TASK_ON_RQ_QUEUED;
activate_task(this_rq, p, 0);
/*
* We continue with the search, just in
@@ -2095,6 +2312,13 @@ static void rq_offline_rt(struct rq *rq)
static void switched_from_rt(struct rq *rq, struct task_struct *p)
{
/*
+ * On class switch from rt, always cancel active schedtune timers,
+ * this handles the cases where we switch class for a task that is
+ * already rt-dequeued but has a running timer.
+ */
+ schedtune_dequeue_rt(rq, p);
+
+ /*
* If there are other RT tasks then we will reschedule
* and the scheduling of the other RT tasks will handle
* the balancing. But if we are the last RT task
@@ -2136,10 +2360,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
#ifdef CONFIG_SMP
if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
queue_push_tasks(rq);
-#else
- if (p->prio < rq->curr->prio)
- resched_curr(rq);
#endif /* CONFIG_SMP */
+ if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq)))
+ resched_curr(rq);
}
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0517abd7dd73..d066a6870245 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,6 +2,7 @@
#include <linux/sched.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/rt.h>
+#include <linux/sched/smt.h>
#include <linux/sched/deadline.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
@@ -31,8 +32,10 @@ extern long calc_load_fold_active(struct rq *this_rq);
#ifdef CONFIG_SMP
extern void update_cpu_load_active(struct rq *this_rq);
+extern void check_for_migration(struct rq *rq, struct task_struct *p);
#else
static inline void update_cpu_load_active(struct rq *this_rq) { }
+static inline void check_for_migration(struct rq *rq, struct task_struct *p) { }
#endif
/*
@@ -233,6 +236,8 @@ struct cfs_bandwidth {
/* statistics */
int nr_periods, nr_throttled;
u64 throttled_time;
+
+ bool distribute_running;
#endif
};
@@ -308,7 +313,7 @@ extern int tg_nop(struct task_group *tg, void *data);
extern void free_fair_sched_group(struct task_group *tg);
extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
-extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
+extern void unregister_fair_sched_group(struct task_group *tg);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
@@ -335,7 +340,15 @@ extern void sched_move_task(struct task_struct *tsk);
#ifdef CONFIG_FAIR_GROUP_SCHED
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
-#endif
+
+#ifdef CONFIG_SMP
+extern void set_task_rq_fair(struct sched_entity *se,
+ struct cfs_rq *prev, struct cfs_rq *next);
+#else /* !CONFIG_SMP */
+static inline void set_task_rq_fair(struct sched_entity *se,
+ struct cfs_rq *prev, struct cfs_rq *next) { }
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
#else /* CONFIG_CGROUP_SCHED */
@@ -376,6 +389,7 @@ struct cfs_rq {
unsigned long runnable_load_avg;
#ifdef CONFIG_FAIR_GROUP_SCHED
unsigned long tg_load_avg_contrib;
+ unsigned long propagate_avg;
#endif
atomic_long_t removed_load_avg, removed_util_avg;
#ifndef CONFIG_64BIT
@@ -410,6 +424,10 @@ struct cfs_rq {
struct list_head leaf_cfs_rq_list;
struct task_group *tg; /* group that "owns" this runqueue */
+#ifdef CONFIG_SCHED_WALT
+ u64 cumulative_runnable_avg;
+#endif
+
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
u64 runtime_expires;
@@ -417,7 +435,7 @@ struct cfs_rq {
u64 throttled_clock, throttled_clock_task;
u64 throttled_clock_task_time;
- int throttled, throttle_count;
+ int throttled, throttle_count, throttle_uptodate;
struct list_head throttled_list;
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -429,7 +447,7 @@ static inline int rt_bandwidth_enabled(void)
}
/* RT IPI pull logic requires IRQ_WORK */
-#ifdef CONFIG_IRQ_WORK
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_SMP)
# define HAVE_RT_PUSH_IPI
#endif
@@ -450,12 +468,6 @@ struct rt_rq {
unsigned long rt_nr_total;
int overloaded;
struct plist_head pushable_tasks;
-#ifdef HAVE_RT_PUSH_IPI
- int push_flags;
- int push_cpu;
- struct irq_work push_work;
- raw_spinlock_t push_lock;
-#endif
#endif /* CONFIG_SMP */
int rt_queued;
@@ -506,10 +518,18 @@ struct dl_rq {
#else
struct dl_bw dl_bw;
#endif
+ /* This is the "average utilization" for this runqueue */
+ s64 avg_bw;
};
#ifdef CONFIG_SMP
+struct max_cpu_capacity {
+ raw_spinlock_t lock;
+ unsigned long val;
+ int cpu;
+};
+
/*
* We add the notion of a root-domain which will be used to define per-domain
* variables. Each exclusive cpuset essentially defines an island domain by
@@ -528,6 +548,9 @@ struct root_domain {
/* Indicate more than one runnable task for any CPU */
bool overload;
+ /* Indicate one or more cpus over-utilized (tipping point) */
+ bool overutilized;
+
/*
* The bit corresponding to a CPU gets set here if such CPU has more
* than one runnable -deadline task (as it is below for RT tasks).
@@ -537,16 +560,40 @@ struct root_domain {
struct dl_bw dl_bw;
struct cpudl cpudl;
+#ifdef HAVE_RT_PUSH_IPI
+ /*
+ * For IPI pull requests, loop across the rto_mask.
+ */
+ struct irq_work rto_push_work;
+ raw_spinlock_t rto_lock;
+ /* These are only updated and read within rto_lock */
+ int rto_loop;
+ int rto_cpu;
+ /* These atomics are updated outside of a lock */
+ atomic_t rto_loop_next;
+ atomic_t rto_loop_start;
+#endif
/*
* The "RT overload" flag: it gets set if a CPU has more than
* one runnable RT task.
*/
cpumask_var_t rto_mask;
struct cpupri cpupri;
+
+ /* Maximum cpu capacity in the system. */
+ struct max_cpu_capacity max_cpu_capacity;
+
+ /* First cpu with maximum and minimum original capacity */
+ int max_cap_orig_cpu, min_cap_orig_cpu;
};
extern struct root_domain def_root_domain;
+extern void sched_get_rd(struct root_domain *rd);
+extern void sched_put_rd(struct root_domain *rd);
+#ifdef HAVE_RT_PUSH_IPI
+extern void rto_push_irq_work_func(struct irq_work *work);
+#endif
#endif /* CONFIG_SMP */
/*
@@ -572,6 +619,7 @@ struct rq {
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
unsigned long last_load_update_tick;
+ unsigned int misfit_task;
#ifdef CONFIG_NO_HZ_COMMON
u64 nohz_stamp;
unsigned long nohz_flags;
@@ -579,6 +627,14 @@ struct rq {
#ifdef CONFIG_NO_HZ_FULL
unsigned long last_sched_tick;
#endif
+
+#ifdef CONFIG_CPU_QUIET
+ /* time-based average load */
+ u64 nr_last_stamp;
+ u64 nr_running_integral;
+ seqcount_t ave_seqcnt;
+#endif
+
/* capture load from *all* tasks on this cpu: */
struct load_weight load;
unsigned long nr_load_updates;
@@ -591,6 +647,7 @@ struct rq {
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
+ struct list_head *tmp_alone_branch;
#endif /* CONFIG_FAIR_GROUP_SCHED */
/*
@@ -624,6 +681,7 @@ struct rq {
/* For active balancing */
int active_balance;
int push_cpu;
+ struct task_struct *push_task;
struct cpu_stop_work active_balance_work;
/* cpu of this runqueue: */
int cpu;
@@ -640,6 +698,20 @@ struct rq {
u64 max_idle_balance_cost;
#endif
+#ifdef CONFIG_SCHED_WALT
+ u64 cumulative_runnable_avg;
+ u64 window_start;
+ u64 curr_runnable_sum;
+ u64 prev_runnable_sum;
+ u64 nt_curr_runnable_sum;
+ u64 nt_prev_runnable_sum;
+ u64 cur_irqload;
+ u64 avg_irqload;
+ u64 irqload_ts;
+ u64 cum_window_demand;
+#endif /* CONFIG_SCHED_WALT */
+
+
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
u64 prev_irq_time;
#endif
@@ -678,6 +750,9 @@ struct rq {
/* try_to_wake_up() stats */
unsigned int ttwu_count;
unsigned int ttwu_local;
+#ifdef CONFIG_SMP
+ struct eas_stats eas_stats;
+#endif
#endif
#ifdef CONFIG_SMP
@@ -687,6 +762,7 @@ struct rq {
#ifdef CONFIG_CPU_IDLE
/* Must be inspected within a rcu lock section */
struct cpuidle_state *idle_state;
+ int idle_state_idx;
#endif
};
@@ -836,6 +912,8 @@ DECLARE_PER_CPU(int, sd_llc_id);
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
DECLARE_PER_CPU(struct sched_domain *, sd_busy);
DECLARE_PER_CPU(struct sched_domain *, sd_asym);
+DECLARE_PER_CPU(struct sched_domain *, sd_ea);
+DECLARE_PER_CPU(struct sched_domain *, sd_scs);
struct sched_group_capacity {
atomic_t ref;
@@ -843,7 +921,9 @@ struct sched_group_capacity {
* CPU capacity of this group, SCHED_LOAD_SCALE being max capacity
* for a single CPU.
*/
- unsigned int capacity;
+ unsigned long capacity;
+ unsigned long max_capacity; /* Max per-cpu capacity in group */
+ unsigned long min_capacity; /* Min per-CPU capacity in group */
unsigned long next_update;
int imbalance; /* XXX unrelated to capacity but shared group state */
/*
@@ -860,6 +940,7 @@ struct sched_group {
unsigned int group_weight;
struct sched_group_capacity *sgc;
+ const struct sched_group_energy *sge;
/*
* The CPUs this group covers.
@@ -933,6 +1014,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
#endif
#ifdef CONFIG_FAIR_GROUP_SCHED
+ set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]);
p->se.cfs_rq = tg->cfs_rq[cpu];
p->se.parent = tg->se[cpu];
#endif
@@ -963,7 +1045,11 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
* per-task data have been completed by this moment.
*/
smp_wmb();
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+ p->cpu = cpu;
+#else
task_thread_info(p)->cpu = cpu;
+#endif
p->wake_cpu = cpu;
#endif
}
@@ -1163,6 +1249,7 @@ static const u32 prio_to_wmult[40] = {
#endif
#define ENQUEUE_REPLENISH 0x08
#define ENQUEUE_RESTORE 0x10
+#define ENQUEUE_WAKEUP_NEW 0x20
#define DEQUEUE_SLEEP 0x01
#define DEQUEUE_SAVE 0x02
@@ -1192,7 +1279,8 @@ struct sched_class {
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
- int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
+ int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags,
+ int subling_count_hint);
void (*migrate_task_rq)(struct task_struct *p);
void (*task_waking) (struct task_struct *task);
@@ -1225,8 +1313,11 @@ struct sched_class {
void (*update_curr) (struct rq *rq);
+#define TASK_SET_GROUP 0
+#define TASK_MOVE_GROUP 1
+
#ifdef CONFIG_FAIR_GROUP_SCHED
- void (*task_move_group) (struct task_struct *p);
+ void (*task_change_group)(struct task_struct *p, int type);
#endif
};
@@ -1248,6 +1339,7 @@ extern const struct sched_class idle_sched_class;
#ifdef CONFIG_SMP
+extern void init_max_cpu_capacity(struct max_cpu_capacity *mcc);
extern void update_group_capacity(struct sched_domain *sd, int cpu);
extern void trigger_load_balance(struct rq *rq);
@@ -1276,6 +1368,17 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq)
WARN_ON(!rcu_read_lock_held());
return rq->idle_state;
}
+
+static inline void idle_set_state_idx(struct rq *rq, int idle_state_idx)
+{
+ rq->idle_state_idx = idle_state_idx;
+}
+
+static inline int idle_get_state_idx(struct rq *rq)
+{
+ WARN_ON(!rcu_read_lock_held());
+ return rq->idle_state_idx;
+}
#else
static inline void idle_set_state(struct rq *rq,
struct cpuidle_state *idle_state)
@@ -1286,6 +1389,15 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq)
{
return NULL;
}
+
+static inline void idle_set_state_idx(struct rq *rq, int idle_state_idx)
+{
+}
+
+static inline int idle_get_state_idx(struct rq *rq)
+{
+ return -1;
+}
#endif
extern void sysrq_sched_debug_show(void);
@@ -1301,6 +1413,7 @@ extern void resched_cpu(int cpu);
extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
+extern void init_rt_schedtune_timer(struct sched_rt_entity *rt_se);
extern struct dl_bandwidth def_dl_bandwidth;
extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
@@ -1309,8 +1422,9 @@ extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
unsigned long to_ratio(u64 period, u64 runtime);
extern void init_entity_runnable_average(struct sched_entity *se);
+extern void post_init_entity_util_avg(struct sched_entity *se);
-static inline void add_nr_running(struct rq *rq, unsigned count)
+static inline void __add_nr_running(struct rq *rq, unsigned count)
{
unsigned prev_nr = rq->nr_running;
@@ -1338,11 +1452,48 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
}
}
-static inline void sub_nr_running(struct rq *rq, unsigned count)
+static inline void __sub_nr_running(struct rq *rq, unsigned count)
{
rq->nr_running -= count;
}
+#ifdef CONFIG_CPU_QUIET
+#define NR_AVE_SCALE(x) ((x) << FSHIFT)
+static inline u64 do_nr_running_integral(struct rq *rq)
+{
+ s64 nr, deltax;
+ u64 nr_running_integral = rq->nr_running_integral;
+
+ deltax = rq->clock_task - rq->nr_last_stamp;
+ nr = NR_AVE_SCALE(rq->nr_running);
+
+ nr_running_integral += nr * deltax;
+
+ return nr_running_integral;
+}
+
+static inline void add_nr_running(struct rq *rq, unsigned count)
+{
+ write_seqcount_begin(&rq->ave_seqcnt);
+ rq->nr_running_integral = do_nr_running_integral(rq);
+ rq->nr_last_stamp = rq->clock_task;
+ __add_nr_running(rq, count);
+ write_seqcount_end(&rq->ave_seqcnt);
+}
+
+static inline void sub_nr_running(struct rq *rq, unsigned count)
+{
+ write_seqcount_begin(&rq->ave_seqcnt);
+ rq->nr_running_integral = do_nr_running_integral(rq);
+ rq->nr_last_stamp = rq->clock_task;
+ __sub_nr_running(rq, count);
+ write_seqcount_end(&rq->ave_seqcnt);
+}
+#else
+#define add_nr_running __add_nr_running
+#define sub_nr_running __sub_nr_running
+#endif
+
static inline void rq_last_tick_reset(struct rq *rq)
{
#ifdef CONFIG_NO_HZ_FULL
@@ -1415,10 +1566,87 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
}
#endif
+#ifdef CONFIG_SMP
+static inline unsigned long capacity_of(int cpu)
+{
+ return cpu_rq(cpu)->cpu_capacity;
+}
+
+static inline unsigned long capacity_orig_of(int cpu)
+{
+ return cpu_rq(cpu)->cpu_capacity_orig;
+}
+
+extern unsigned int sysctl_sched_use_walt_cpu_util;
+extern unsigned int walt_ravg_window;
+extern bool walt_disabled;
+
+/*
+ * cpu_util returns the amount of capacity of a CPU that is used by CFS
+ * tasks. The unit of the return value must be the one of capacity so we can
+ * compare the utilization with the capacity of the CPU that is available for
+ * CFS task (ie cpu_capacity).
+ *
+ * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the
+ * recent utilization of currently non-runnable tasks on a CPU. It represents
+ * the amount of utilization of a CPU in the range [0..capacity_orig] where
+ * capacity_orig is the cpu_capacity available at the highest frequency
+ * (arch_scale_freq_capacity()).
+ * The utilization of a CPU converges towards a sum equal to or less than the
+ * current capacity (capacity_curr <= capacity_orig) of the CPU because it is
+ * the running time on this CPU scaled by capacity_curr.
+ *
+ * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even
+ * higher than capacity_orig because of unfortunate rounding in
+ * cfs.avg.util_avg or just after migrating tasks and new task wakeups until
+ * the average stabilizes with the new running time. We need to check that the
+ * utilization stays within the range of [0..capacity_orig] and cap it if
+ * necessary. Without utilization capping, a group could be seen as overloaded
+ * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of
+ * available capacity. We allow utilization to overshoot capacity_curr (but not
+ * capacity_orig) as it useful for predicting the capacity required after task
+ * migrations (scheduler-driven DVFS).
+ */
+static inline unsigned long __cpu_util(int cpu, int delta)
+{
+ unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
+ unsigned long capacity = capacity_orig_of(cpu);
+
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util)
+ util = div64_u64(cpu_rq(cpu)->cumulative_runnable_avg,
+ walt_ravg_window >> SCHED_LOAD_SHIFT);
+#endif
+ delta += util;
+ if (delta < 0)
+ return 0;
+
+ return (delta >= capacity) ? capacity : delta;
+}
+
+static inline unsigned long cpu_util(int cpu)
+{
+ return __cpu_util(cpu, 0);
+}
+
+static inline unsigned long cpu_util_freq(int cpu)
+{
+ unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg;
+ unsigned long capacity = capacity_orig_of(cpu);
+
+#ifdef CONFIG_SCHED_WALT
+ if (!walt_disabled && sysctl_sched_use_walt_cpu_util)
+ util = div64_u64(cpu_rq(cpu)->prev_runnable_sum,
+ walt_ravg_window >> SCHED_LOAD_SHIFT);
+#endif
+ return (util >= capacity) ? capacity : util;
+}
+
+#endif
+
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));
- sched_avg_update(rq);
}
#else
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
@@ -1507,6 +1735,9 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
}
+extern struct rq *lock_rq_of(struct task_struct *p, unsigned long *flags);
+extern void unlock_rq_of(struct rq *rq, struct task_struct *p, unsigned long *flags);
+
#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT
@@ -1579,7 +1810,8 @@ static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
- raw_spin_unlock(&busiest->lock);
+ if (this_rq != busiest)
+ raw_spin_unlock(&busiest->lock);
lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
@@ -1771,15 +2003,65 @@ static inline u64 irq_time_read(int cpu)
#endif /* CONFIG_64BIT */
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-static inline void account_reset_rq(struct rq *rq)
+#ifdef CONFIG_CPU_FREQ
+DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_update_util - Take a note about CPU utilization changes.
+ * @rq: Runqueue to carry out the update for.
+ * @flags: Update reason flags.
+ *
+ * This function is called by the scheduler on the CPU whose utilization is
+ * being updated.
+ *
+ * It can only be called from RCU-sched read-side critical sections.
+ *
+ * The way cpufreq is currently arranged requires it to evaluate the CPU
+ * performance state (frequency/voltage) on a regular basis to prevent it from
+ * being stuck in a completely inadequate performance level for too long.
+ * That is not guaranteed to happen if the updates are only triggered from CFS,
+ * though, because they may not be coming in if RT or deadline tasks are active
+ * all the time (or there are RT and DL tasks only).
+ *
+ * As a workaround for that issue, this function is called by the RT and DL
+ * sched classes to trigger extra cpufreq updates to prevent it from stalling,
+ * but that really is a band-aid. Going forward it should be replaced with
+ * solutions targeted more specifically at RT and DL tasks.
+ */
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
{
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
- rq->prev_irq_time = 0;
-#endif
-#ifdef CONFIG_PARAVIRT
- rq->prev_steal_time = 0;
+ struct update_util_data *data;
+
+ data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+ if (data)
+ data->func(data, rq_clock(rq), flags);
+}
+
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags)
+{
+ if (cpu_of(rq) == smp_processor_id())
+ cpufreq_update_util(rq, flags);
+}
+#else
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {}
+#endif /* CONFIG_CPU_FREQ */
+
+#ifdef CONFIG_SCHED_WALT
+
+static inline bool
+walt_task_in_cum_window_demand(struct rq *rq, struct task_struct *p)
+{
+ return cpu_of(rq) == task_cpu(p) &&
+ (p->on_rq || p->last_sleep_ts >= rq->window_start);
+}
+
+#endif /* CONFIG_SCHED_WALT */
+
+#ifdef arch_scale_freq_capacity
+#ifndef arch_scale_freq_invariant
+#define arch_scale_freq_invariant() (true)
#endif
-#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
- rq->prev_steal_time_rq = 0;
+#else /* arch_scale_freq_capacity */
+#define arch_scale_freq_invariant() (false)
#endif
-}
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 87e2c9f0c33e..6d74a7c77c8c 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -12,6 +12,28 @@
*/
#define SCHEDSTAT_VERSION 15
+#ifdef CONFIG_SMP
+static inline void show_easstat(struct seq_file *seq, struct eas_stats *stats)
+{
+ /* eas-specific runqueue stats */
+ seq_printf(seq, "eas %llu %llu %llu %llu %llu %llu ",
+ stats->sis_attempts, stats->sis_idle, stats->sis_cache_affine,
+ stats->sis_suff_cap, stats->sis_idle_cpu, stats->sis_count);
+
+ seq_printf(seq, "%llu %llu %llu %llu %llu %llu %llu ",
+ stats->secb_attempts, stats->secb_sync, stats->secb_idle_bt,
+ stats->secb_insuff_cap, stats->secb_no_nrg_sav,
+ stats->secb_nrg_sav, stats->secb_count);
+
+ seq_printf(seq, "%llu %llu %llu %llu %llu ",
+ stats->fbt_attempts, stats->fbt_no_cpu, stats->fbt_no_sd,
+ stats->fbt_pref_idle, stats->fbt_count);
+
+ seq_printf(seq, "%llu %llu\n",
+ stats->cas_attempts, stats->cas_count);
+}
+#endif
+
static int show_schedstat(struct seq_file *seq, void *v)
{
int cpu;
@@ -40,6 +62,8 @@ static int show_schedstat(struct seq_file *seq, void *v)
seq_printf(seq, "\n");
#ifdef CONFIG_SMP
+ show_easstat(seq, &rq->eas_stats);
+
/* domain-specific stats */
rcu_read_lock();
for_each_domain(cpu, sd) {
@@ -66,6 +90,8 @@ static int show_schedstat(struct seq_file *seq, void *v)
sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed,
sd->ttwu_wake_remote, sd->ttwu_move_affine,
sd->ttwu_move_balance);
+
+ show_easstat(seq, &sd->eas_stats);
}
rcu_read_unlock();
#endif
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index cbc67da10954..a5567ccd8803 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -1,4 +1,5 @@
#include "sched.h"
+#include "walt.h"
/*
* stop-task scheduling class.
@@ -11,7 +12,8 @@
#ifdef CONFIG_SMP
static int
-select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags,
+ int sibling_count_hint)
{
return task_cpu(p); /* stop tasks as never migrate */
}
@@ -42,12 +44,14 @@ static void
enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
add_nr_running(rq, 1);
+ walt_inc_cumulative_runnable_avg(rq, p);
}
static void
dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
{
sub_nr_running(rq, 1);
+ walt_dec_cumulative_runnable_avg(rq, p);
}
static void yield_task_stop(struct rq *rq)
diff --git a/kernel/sched/tune.c b/kernel/sched/tune.c
new file mode 100644
index 000000000000..5e47c29b44f6
--- /dev/null
+++ b/kernel/sched/tune.c
@@ -0,0 +1,955 @@
+#include <linux/cgroup.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/printk.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
+
+#include <trace/events/sched.h>
+
+#include "sched.h"
+#include "tune.h"
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+bool schedtune_initialized = false;
+#endif
+
+unsigned int sysctl_sched_cfs_boost __read_mostly;
+
+extern struct reciprocal_value schedtune_spc_rdiv;
+extern struct target_nrg schedtune_target_nrg;
+
+/* Performance Boost region (B) threshold params */
+static int perf_boost_idx;
+
+/* Performance Constraint region (C) threshold params */
+static int perf_constrain_idx;
+
+/**
+ * Performance-Energy (P-E) Space thresholds constants
+ */
+struct threshold_params {
+ int nrg_gain;
+ int cap_gain;
+};
+
+/*
+ * System specific P-E space thresholds constants
+ */
+static struct threshold_params
+threshold_gains[] = {
+ { 0, 5 }, /* < 10% */
+ { 1, 5 }, /* < 20% */
+ { 2, 5 }, /* < 30% */
+ { 3, 5 }, /* < 40% */
+ { 4, 5 }, /* < 50% */
+ { 5, 4 }, /* < 60% */
+ { 5, 3 }, /* < 70% */
+ { 5, 2 }, /* < 80% */
+ { 5, 1 }, /* < 90% */
+ { 5, 0 } /* <= 100% */
+};
+
+static int
+__schedtune_accept_deltas(int nrg_delta, int cap_delta,
+ int perf_boost_idx, int perf_constrain_idx)
+{
+ int payoff = -INT_MAX;
+ int gain_idx = -1;
+
+ /* Performance Boost (B) region */
+ if (nrg_delta >= 0 && cap_delta > 0)
+ gain_idx = perf_boost_idx;
+ /* Performance Constraint (C) region */
+ else if (nrg_delta < 0 && cap_delta <= 0)
+ gain_idx = perf_constrain_idx;
+
+ /* Default: reject schedule candidate */
+ if (gain_idx == -1)
+ return payoff;
+
+ /*
+ * Evaluate "Performance Boost" vs "Energy Increase"
+ *
+ * - Performance Boost (B) region
+ *
+ * Condition: nrg_delta > 0 && cap_delta > 0
+ * Payoff criteria:
+ * cap_gain / nrg_gain < cap_delta / nrg_delta =
+ * cap_gain * nrg_delta < cap_delta * nrg_gain
+ * Note that since both nrg_gain and nrg_delta are positive, the
+ * inequality does not change. Thus:
+ *
+ * payoff = (cap_delta * nrg_gain) - (cap_gain * nrg_delta)
+ *
+ * - Performance Constraint (C) region
+ *
+ * Condition: nrg_delta < 0 && cap_delta < 0
+ * payoff criteria:
+ * cap_gain / nrg_gain > cap_delta / nrg_delta =
+ * cap_gain * nrg_delta < cap_delta * nrg_gain
+ * Note that since nrg_gain > 0 while nrg_delta < 0, the
+ * inequality change. Thus:
+ *
+ * payoff = (cap_delta * nrg_gain) - (cap_gain * nrg_delta)
+ *
+ * This means that, in case of same positive defined {cap,nrg}_gain
+ * for both the B and C regions, we can use the same payoff formula
+ * where a positive value represents the accept condition.
+ */
+ payoff = cap_delta * threshold_gains[gain_idx].nrg_gain;
+ payoff -= nrg_delta * threshold_gains[gain_idx].cap_gain;
+
+ return payoff;
+}
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+
+/*
+ * EAS scheduler tunables for task groups.
+ */
+
+/* SchdTune tunables for a group of tasks */
+struct schedtune {
+ /* SchedTune CGroup subsystem */
+ struct cgroup_subsys_state css;
+
+ /* Boost group allocated ID */
+ int idx;
+
+ /* Boost value for tasks on that SchedTune CGroup */
+ int boost;
+
+ /* Performance Boost (B) region threshold params */
+ int perf_boost_idx;
+
+ /* Performance Constraint (C) region threshold params */
+ int perf_constrain_idx;
+
+ /* Hint to bias scheduling of tasks on that SchedTune CGroup
+ * towards idle CPUs */
+ int prefer_idle;
+};
+
+static inline struct schedtune *css_st(struct cgroup_subsys_state *css)
+{
+ return css ? container_of(css, struct schedtune, css) : NULL;
+}
+
+static inline struct schedtune *task_schedtune(struct task_struct *tsk)
+{
+ return css_st(task_css(tsk, schedtune_cgrp_id));
+}
+
+static inline struct schedtune *parent_st(struct schedtune *st)
+{
+ return css_st(st->css.parent);
+}
+
+/*
+ * SchedTune root control group
+ * The root control group is used to defined a system-wide boosting tuning,
+ * which is applied to all tasks in the system.
+ * Task specific boost tuning could be specified by creating and
+ * configuring a child control group under the root one.
+ * By default, system-wide boosting is disabled, i.e. no boosting is applied
+ * to tasks which are not into a child control group.
+ */
+static struct schedtune
+root_schedtune = {
+ .boost = 0,
+ .perf_boost_idx = 0,
+ .perf_constrain_idx = 0,
+ .prefer_idle = 0,
+};
+
+int
+schedtune_accept_deltas(int nrg_delta, int cap_delta,
+ struct task_struct *task)
+{
+ struct schedtune *ct;
+ int perf_boost_idx;
+ int perf_constrain_idx;
+
+ /* Optimal (O) region */
+ if (nrg_delta < 0 && cap_delta > 0) {
+ trace_sched_tune_filter(nrg_delta, cap_delta, 0, 0, 1, 0);
+ return INT_MAX;
+ }
+
+ /* Suboptimal (S) region */
+ if (nrg_delta > 0 && cap_delta < 0) {
+ trace_sched_tune_filter(nrg_delta, cap_delta, 0, 0, -1, 5);
+ return -INT_MAX;
+ }
+
+ /* Get task specific perf Boost/Constraints indexes */
+ rcu_read_lock();
+ ct = task_schedtune(task);
+ perf_boost_idx = ct->perf_boost_idx;
+ perf_constrain_idx = ct->perf_constrain_idx;
+ rcu_read_unlock();
+
+ return __schedtune_accept_deltas(nrg_delta, cap_delta,
+ perf_boost_idx, perf_constrain_idx);
+}
+
+/*
+ * Maximum number of boost groups to support
+ * When per-task boosting is used we still allow only limited number of
+ * boost groups for two main reasons:
+ * 1. on a real system we usually have only few classes of workloads which
+ * make sense to boost with different values (e.g. background vs foreground
+ * tasks, interactive vs low-priority tasks)
+ * 2. a limited number allows for a simpler and more memory/time efficient
+ * implementation especially for the computation of the per-CPU boost
+ * value
+ */
+#define BOOSTGROUPS_COUNT 5
+
+/* Array of configured boostgroups */
+static struct schedtune *allocated_group[BOOSTGROUPS_COUNT] = {
+ &root_schedtune,
+ NULL,
+};
+
+/* SchedTune boost groups
+ * Keep track of all the boost groups which impact on CPU, for example when a
+ * CPU has two RUNNABLE tasks belonging to two different boost groups and thus
+ * likely with different boost values.
+ * Since on each system we expect only a limited number of boost groups, here
+ * we use a simple array to keep track of the metrics required to compute the
+ * maximum per-CPU boosting value.
+ */
+struct boost_groups {
+ /* Maximum boost value for all RUNNABLE tasks on a CPU */
+ bool idle;
+ int boost_max;
+ struct {
+ /* The boost for tasks on that boost group */
+ int boost;
+ /* Count of RUNNABLE tasks on that boost group */
+ unsigned tasks;
+ } group[BOOSTGROUPS_COUNT];
+ /* CPU's boost group locking */
+ raw_spinlock_t lock;
+};
+
+/* Boost groups affecting each CPU in the system */
+DEFINE_PER_CPU(struct boost_groups, cpu_boost_groups);
+
+static void
+schedtune_cpu_update(int cpu)
+{
+ struct boost_groups *bg;
+ int boost_max;
+ int idx;
+
+ bg = &per_cpu(cpu_boost_groups, cpu);
+
+ /* The root boost group is always active */
+ boost_max = bg->group[0].boost;
+ for (idx = 1; idx < BOOSTGROUPS_COUNT; ++idx) {
+ /*
+ * A boost group affects a CPU only if it has
+ * RUNNABLE tasks on that CPU
+ */
+ if (bg->group[idx].tasks == 0)
+ continue;
+
+ boost_max = max(boost_max, bg->group[idx].boost);
+ }
+ /* Ensures boost_max is non-negative when all cgroup boost values
+ * are neagtive. Avoids under-accounting of cpu capacity which may cause
+ * task stacking and frequency spikes.*/
+ boost_max = max(boost_max, 0);
+ bg->boost_max = boost_max;
+}
+
+static int
+schedtune_boostgroup_update(int idx, int boost)
+{
+ struct boost_groups *bg;
+ int cur_boost_max;
+ int old_boost;
+ int cpu;
+
+ /* Update per CPU boost groups */
+ for_each_possible_cpu(cpu) {
+ bg = &per_cpu(cpu_boost_groups, cpu);
+
+ /*
+ * Keep track of current boost values to compute the per CPU
+ * maximum only when it has been affected by the new value of
+ * the updated boost group
+ */
+ cur_boost_max = bg->boost_max;
+ old_boost = bg->group[idx].boost;
+
+ /* Update the boost value of this boost group */
+ bg->group[idx].boost = boost;
+
+ /* Check if this update increase current max */
+ if (boost > cur_boost_max && bg->group[idx].tasks) {
+ bg->boost_max = boost;
+ trace_sched_tune_boostgroup_update(cpu, 1, bg->boost_max);
+ continue;
+ }
+
+ /* Check if this update has decreased current max */
+ if (cur_boost_max == old_boost && old_boost > boost) {
+ schedtune_cpu_update(cpu);
+ trace_sched_tune_boostgroup_update(cpu, -1, bg->boost_max);
+ continue;
+ }
+
+ trace_sched_tune_boostgroup_update(cpu, 0, bg->boost_max);
+ }
+
+ return 0;
+}
+
+#define ENQUEUE_TASK 1
+#define DEQUEUE_TASK -1
+
+static inline void
+schedtune_tasks_update(struct task_struct *p, int cpu, int idx, int task_count)
+{
+ struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
+ int tasks = bg->group[idx].tasks + task_count;
+
+ /* Update boosted tasks count while avoiding to make it negative */
+ bg->group[idx].tasks = max(0, tasks);
+
+ trace_sched_tune_tasks_update(p, cpu, tasks, idx,
+ bg->group[idx].boost, bg->boost_max);
+
+ /* Boost group activation or deactivation on that RQ */
+ if (tasks == 1 || tasks == 0)
+ schedtune_cpu_update(cpu);
+}
+
+/*
+ * NOTE: This function must be called while holding the lock on the CPU RQ
+ */
+void schedtune_enqueue_task(struct task_struct *p, int cpu)
+{
+ struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
+ unsigned long irq_flags;
+ struct schedtune *st;
+ int idx;
+
+ if (!unlikely(schedtune_initialized))
+ return;
+
+ /*
+ * When a task is marked PF_EXITING by do_exit() it's going to be
+ * dequeued and enqueued multiple times in the exit path.
+ * Thus we avoid any further update, since we do not want to change
+ * CPU boosting while the task is exiting.
+ */
+ if (p->flags & PF_EXITING)
+ return;
+
+ /*
+ * Boost group accouting is protected by a per-cpu lock and requires
+ * interrupt to be disabled to avoid race conditions for example on
+ * do_exit()::cgroup_exit() and task migration.
+ */
+ raw_spin_lock_irqsave(&bg->lock, irq_flags);
+ rcu_read_lock();
+
+ st = task_schedtune(p);
+ idx = st->idx;
+
+ schedtune_tasks_update(p, cpu, idx, ENQUEUE_TASK);
+
+ rcu_read_unlock();
+ raw_spin_unlock_irqrestore(&bg->lock, irq_flags);
+}
+
+int schedtune_can_attach(struct cgroup_taskset *tset)
+{
+ struct task_struct *task;
+ struct cgroup_subsys_state *css;
+ struct boost_groups *bg;
+ unsigned long irq_flags;
+ unsigned int cpu;
+ struct rq *rq;
+ int src_bg; /* Source boost group index */
+ int dst_bg; /* Destination boost group index */
+ int tasks;
+
+ if (!unlikely(schedtune_initialized))
+ return 0;
+
+
+ cgroup_taskset_for_each(task, css, tset) {
+
+ /*
+ * Lock the CPU's RQ the task is enqueued to avoid race
+ * conditions with migration code while the task is being
+ * accounted
+ */
+ rq = lock_rq_of(task, &irq_flags);
+
+ if (!task->on_rq) {
+ unlock_rq_of(rq, task, &irq_flags);
+ continue;
+ }
+
+ /*
+ * Boost group accouting is protected by a per-cpu lock and requires
+ * interrupt to be disabled to avoid race conditions on...
+ */
+ cpu = cpu_of(rq);
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ raw_spin_lock(&bg->lock);
+
+ dst_bg = css_st(css)->idx;
+ src_bg = task_schedtune(task)->idx;
+
+ /*
+ * Current task is not changing boostgroup, which can
+ * happen when the new hierarchy is in use.
+ */
+ if (unlikely(dst_bg == src_bg)) {
+ raw_spin_unlock(&bg->lock);
+ unlock_rq_of(rq, task, &irq_flags);
+ continue;
+ }
+
+ /*
+ * This is the case of a RUNNABLE task which is switching its
+ * current boost group.
+ */
+
+ /* Move task from src to dst boost group */
+ tasks = bg->group[src_bg].tasks - 1;
+ bg->group[src_bg].tasks = max(0, tasks);
+ bg->group[dst_bg].tasks += 1;
+
+ raw_spin_unlock(&bg->lock);
+ unlock_rq_of(rq, task, &irq_flags);
+
+ /* Update CPU boost group */
+ if (bg->group[src_bg].tasks == 0 || bg->group[dst_bg].tasks == 1)
+ schedtune_cpu_update(task_cpu(task));
+
+ }
+
+ return 0;
+}
+
+void schedtune_cancel_attach(struct cgroup_taskset *tset)
+{
+ /* This can happen only if SchedTune controller is mounted with
+ * other hierarchies ane one of them fails. Since usually SchedTune is
+ * mouted on its own hierarcy, for the time being we do not implement
+ * a proper rollback mechanism */
+ WARN(1, "SchedTune cancel attach not implemented");
+}
+
+/*
+ * NOTE: This function must be called while holding the lock on the CPU RQ
+ */
+void schedtune_dequeue_task(struct task_struct *p, int cpu)
+{
+ struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu);
+ unsigned long irq_flags;
+ struct schedtune *st;
+ int idx;
+
+ if (!unlikely(schedtune_initialized))
+ return;
+
+ /*
+ * When a task is marked PF_EXITING by do_exit() it's going to be
+ * dequeued and enqueued multiple times in the exit path.
+ * Thus we avoid any further update, since we do not want to change
+ * CPU boosting while the task is exiting.
+ * The last dequeue is already enforce by the do_exit() code path
+ * via schedtune_exit_task().
+ */
+ if (p->flags & PF_EXITING)
+ return;
+
+ /*
+ * Boost group accouting is protected by a per-cpu lock and requires
+ * interrupt to be disabled to avoid race conditions on...
+ */
+ raw_spin_lock_irqsave(&bg->lock, irq_flags);
+ rcu_read_lock();
+
+ st = task_schedtune(p);
+ idx = st->idx;
+
+ schedtune_tasks_update(p, cpu, idx, DEQUEUE_TASK);
+
+ rcu_read_unlock();
+ raw_spin_unlock_irqrestore(&bg->lock, irq_flags);
+}
+
+void schedtune_exit_task(struct task_struct *tsk)
+{
+ struct schedtune *st;
+ unsigned long irq_flags;
+ unsigned int cpu;
+ struct rq *rq;
+ int idx;
+
+ if (!unlikely(schedtune_initialized))
+ return;
+
+ rq = lock_rq_of(tsk, &irq_flags);
+ rcu_read_lock();
+
+ cpu = cpu_of(rq);
+ st = task_schedtune(tsk);
+ idx = st->idx;
+ schedtune_tasks_update(tsk, cpu, idx, DEQUEUE_TASK);
+
+ rcu_read_unlock();
+ unlock_rq_of(rq, tsk, &irq_flags);
+}
+
+int schedtune_cpu_boost(int cpu)
+{
+ struct boost_groups *bg;
+
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ return bg->boost_max;
+}
+
+int schedtune_task_boost(struct task_struct *p)
+{
+ struct schedtune *st;
+ int task_boost;
+
+ if (!unlikely(schedtune_initialized))
+ return 0;
+
+ /* Get task boost value */
+ rcu_read_lock();
+ st = task_schedtune(p);
+ task_boost = st->boost;
+ rcu_read_unlock();
+
+ return task_boost;
+}
+
+int schedtune_prefer_idle(struct task_struct *p)
+{
+ struct schedtune *st;
+ int prefer_idle;
+
+ if (!unlikely(schedtune_initialized))
+ return 0;
+
+ /* Get prefer_idle value */
+ rcu_read_lock();
+ st = task_schedtune(p);
+ prefer_idle = st->prefer_idle;
+ rcu_read_unlock();
+
+ return prefer_idle;
+}
+
+static u64
+prefer_idle_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+ struct schedtune *st = css_st(css);
+
+ return st->prefer_idle;
+}
+
+static int
+prefer_idle_write(struct cgroup_subsys_state *css, struct cftype *cft,
+ u64 prefer_idle)
+{
+ struct schedtune *st = css_st(css);
+ st->prefer_idle = !!prefer_idle;
+
+ return 0;
+}
+
+static s64
+boost_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+ struct schedtune *st = css_st(css);
+
+ return st->boost;
+}
+
+static int
+boost_write(struct cgroup_subsys_state *css, struct cftype *cft,
+ s64 boost)
+{
+ struct schedtune *st = css_st(css);
+ unsigned threshold_idx;
+ int boost_pct;
+
+ if (boost < -100 || boost > 100)
+ return -EINVAL;
+ boost_pct = boost;
+
+ /*
+ * Update threshold params for Performance Boost (B)
+ * and Performance Constraint (C) regions.
+ * The current implementatio uses the same cuts for both
+ * B and C regions.
+ */
+ threshold_idx = clamp(boost_pct, 0, 99) / 10;
+ st->perf_boost_idx = threshold_idx;
+ st->perf_constrain_idx = threshold_idx;
+
+ st->boost = boost;
+ if (css == &root_schedtune.css) {
+ sysctl_sched_cfs_boost = boost;
+ perf_boost_idx = threshold_idx;
+ perf_constrain_idx = threshold_idx;
+ }
+
+ /* Update CPU boost */
+ schedtune_boostgroup_update(st->idx, st->boost);
+
+ trace_sched_tune_config(st->boost);
+
+ return 0;
+}
+
+static struct cftype files[] = {
+ {
+ .name = "boost",
+ .read_s64 = boost_read,
+ .write_s64 = boost_write,
+ },
+ {
+ .name = "prefer_idle",
+ .read_u64 = prefer_idle_read,
+ .write_u64 = prefer_idle_write,
+ },
+ { } /* terminate */
+};
+
+static int
+schedtune_boostgroup_init(struct schedtune *st)
+{
+ struct boost_groups *bg;
+ int cpu;
+
+ /* Keep track of allocated boost groups */
+ allocated_group[st->idx] = st;
+
+ /* Initialize the per CPU boost groups */
+ for_each_possible_cpu(cpu) {
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ bg->group[st->idx].boost = 0;
+ bg->group[st->idx].tasks = 0;
+ }
+
+ return 0;
+}
+
+static struct cgroup_subsys_state *
+schedtune_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+ struct schedtune *st;
+ int idx;
+
+ if (!parent_css)
+ return &root_schedtune.css;
+
+ /* Allow only single level hierachies */
+ if (parent_css != &root_schedtune.css) {
+ pr_err("Nested SchedTune boosting groups not allowed\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ /* Allow only a limited number of boosting groups */
+ for (idx = 1; idx < BOOSTGROUPS_COUNT; ++idx)
+ if (!allocated_group[idx])
+ break;
+ if (idx == BOOSTGROUPS_COUNT) {
+ pr_err("Trying to create more than %d SchedTune boosting groups\n",
+ BOOSTGROUPS_COUNT);
+ return ERR_PTR(-ENOSPC);
+ }
+
+ st = kzalloc(sizeof(*st), GFP_KERNEL);
+ if (!st)
+ goto out;
+
+ /* Initialize per CPUs boost group support */
+ st->idx = idx;
+ if (schedtune_boostgroup_init(st))
+ goto release;
+
+ return &st->css;
+
+release:
+ kfree(st);
+out:
+ return ERR_PTR(-ENOMEM);
+}
+
+static void
+schedtune_boostgroup_release(struct schedtune *st)
+{
+ /* Reset this boost group */
+ schedtune_boostgroup_update(st->idx, 0);
+
+ /* Keep track of allocated boost groups */
+ allocated_group[st->idx] = NULL;
+}
+
+static void
+schedtune_css_free(struct cgroup_subsys_state *css)
+{
+ struct schedtune *st = css_st(css);
+
+ schedtune_boostgroup_release(st);
+ kfree(st);
+}
+
+struct cgroup_subsys schedtune_cgrp_subsys = {
+ .css_alloc = schedtune_css_alloc,
+ .css_free = schedtune_css_free,
+ .can_attach = schedtune_can_attach,
+ .cancel_attach = schedtune_cancel_attach,
+ .legacy_cftypes = files,
+ .early_init = 1,
+};
+
+static inline void
+schedtune_init_cgroups(void)
+{
+ struct boost_groups *bg;
+ int cpu;
+
+ /* Initialize the per CPU boost groups */
+ for_each_possible_cpu(cpu) {
+ bg = &per_cpu(cpu_boost_groups, cpu);
+ memset(bg, 0, sizeof(struct boost_groups));
+ raw_spin_lock_init(&bg->lock);
+ }
+
+ pr_info("schedtune: configured to support %d boost groups\n",
+ BOOSTGROUPS_COUNT);
+
+ schedtune_initialized = true;
+}
+
+#else /* CONFIG_CGROUP_SCHEDTUNE */
+
+int
+schedtune_accept_deltas(int nrg_delta, int cap_delta,
+ struct task_struct *task)
+{
+ /* Optimal (O) region */
+ if (nrg_delta < 0 && cap_delta > 0) {
+ trace_sched_tune_filter(nrg_delta, cap_delta, 0, 0, 1, 0);
+ return INT_MAX;
+ }
+
+ /* Suboptimal (S) region */
+ if (nrg_delta > 0 && cap_delta < 0) {
+ trace_sched_tune_filter(nrg_delta, cap_delta, 0, 0, -1, 5);
+ return -INT_MAX;
+ }
+
+ return __schedtune_accept_deltas(nrg_delta, cap_delta,
+ perf_boost_idx, perf_constrain_idx);
+}
+
+#endif /* CONFIG_CGROUP_SCHEDTUNE */
+
+int
+sysctl_sched_cfs_boost_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ unsigned threshold_idx;
+ int boost_pct;
+
+ if (ret || !write)
+ return ret;
+
+ if (sysctl_sched_cfs_boost < -100 || sysctl_sched_cfs_boost > 100)
+ return -EINVAL;
+ boost_pct = sysctl_sched_cfs_boost;
+
+ /*
+ * Update threshold params for Performance Boost (B)
+ * and Performance Constraint (C) regions.
+ * The current implementatio uses the same cuts for both
+ * B and C regions.
+ */
+ threshold_idx = clamp(boost_pct, 0, 99) / 10;
+ perf_boost_idx = threshold_idx;
+ perf_constrain_idx = threshold_idx;
+
+ return 0;
+}
+
+#ifdef CONFIG_SCHED_DEBUG
+static void
+schedtune_test_nrg(unsigned long delta_pwr)
+{
+ unsigned long test_delta_pwr;
+ unsigned long test_norm_pwr;
+ int idx;
+
+ /*
+ * Check normalization constants using some constant system
+ * energy values
+ */
+ pr_info("schedtune: verify normalization constants...\n");
+ for (idx = 0; idx < 6; ++idx) {
+ test_delta_pwr = delta_pwr >> idx;
+
+ /* Normalize on max energy for target platform */
+ test_norm_pwr = reciprocal_divide(
+ test_delta_pwr << SCHED_LOAD_SHIFT,
+ schedtune_target_nrg.rdiv);
+
+ pr_info("schedtune: max_pwr/2^%d: %4lu => norm_pwr: %5lu\n",
+ idx, test_delta_pwr, test_norm_pwr);
+ }
+}
+#else
+#define schedtune_test_nrg(delta_pwr)
+#endif
+
+/*
+ * Compute the min/max power consumption of a cluster and all its CPUs
+ */
+static void
+schedtune_add_cluster_nrg(
+ struct sched_domain *sd,
+ struct sched_group *sg,
+ struct target_nrg *ste)
+{
+ struct sched_domain *sd2;
+ struct sched_group *sg2;
+
+ struct cpumask *cluster_cpus;
+ char str[32];
+
+ unsigned long min_pwr;
+ unsigned long max_pwr;
+ int cpu;
+
+ /* Get Cluster energy using EM data for the first CPU */
+ cluster_cpus = sched_group_cpus(sg);
+ snprintf(str, 32, "CLUSTER[%*pbl]",
+ cpumask_pr_args(cluster_cpus));
+
+ min_pwr = sg->sge->idle_states[sg->sge->nr_idle_states - 1].power;
+ max_pwr = sg->sge->cap_states[sg->sge->nr_cap_states - 1].power;
+ pr_info("schedtune: %-17s min_pwr: %5lu max_pwr: %5lu\n",
+ str, min_pwr, max_pwr);
+
+ /*
+ * Keep track of this cluster's energy in the computation of the
+ * overall system energy
+ */
+ ste->min_power += min_pwr;
+ ste->max_power += max_pwr;
+
+ /* Get CPU energy using EM data for each CPU in the group */
+ for_each_cpu(cpu, cluster_cpus) {
+ /* Get a SD view for the specific CPU */
+ for_each_domain(cpu, sd2) {
+ /* Get the CPU group */
+ sg2 = sd2->groups;
+ min_pwr = sg2->sge->idle_states[sg2->sge->nr_idle_states - 1].power;
+ max_pwr = sg2->sge->cap_states[sg2->sge->nr_cap_states - 1].power;
+
+ ste->min_power += min_pwr;
+ ste->max_power += max_pwr;
+
+ snprintf(str, 32, "CPU[%d]", cpu);
+ pr_info("schedtune: %-17s min_pwr: %5lu max_pwr: %5lu\n",
+ str, min_pwr, max_pwr);
+
+ /*
+ * Assume we have EM data only at the CPU and
+ * the upper CLUSTER level
+ */
+ BUG_ON(!cpumask_equal(
+ sched_group_cpus(sg),
+ sched_group_cpus(sd2->parent->groups)
+ ));
+ break;
+ }
+ }
+}
+
+/*
+ * Initialize the constants required to compute normalized energy.
+ * The values of these constants depends on the EM data for the specific
+ * target system and topology.
+ * Thus, this function is expected to be called by the code
+ * that bind the EM to the topology information.
+ */
+static int
+schedtune_init(void)
+{
+ struct target_nrg *ste = &schedtune_target_nrg;
+ unsigned long delta_pwr = 0;
+ struct sched_domain *sd;
+ struct sched_group *sg;
+
+ pr_info("schedtune: init normalization constants...\n");
+ ste->max_power = 0;
+ ste->min_power = 0;
+
+ rcu_read_lock();
+
+ /*
+ * When EAS is in use, we always have a pointer to the highest SD
+ * which provides EM data.
+ */
+ sd = rcu_dereference(per_cpu(sd_ea, cpumask_first(cpu_online_mask)));
+ if (!sd) {
+ pr_info("schedtune: no energy model data\n");
+ goto nodata;
+ }
+
+ sg = sd->groups;
+ do {
+ schedtune_add_cluster_nrg(sd, sg, ste);
+ } while (sg = sg->next, sg != sd->groups);
+
+ rcu_read_unlock();
+
+ pr_info("schedtune: %-17s min_pwr: %5lu max_pwr: %5lu\n",
+ "SYSTEM", ste->min_power, ste->max_power);
+
+ /* Compute normalization constants */
+ delta_pwr = ste->max_power - ste->min_power;
+ ste->rdiv = reciprocal_value(delta_pwr);
+ pr_info("schedtune: using normalization constants mul: %u sh1: %u sh2: %u\n",
+ ste->rdiv.m, ste->rdiv.sh1, ste->rdiv.sh2);
+
+ schedtune_test_nrg(delta_pwr);
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+ schedtune_init_cgroups();
+#else
+ pr_info("schedtune: configured to support global boosting only\n");
+#endif
+
+ schedtune_spc_rdiv = reciprocal_value(100);
+
+ return 0;
+
+nodata:
+ pr_warning("schedtune: disabled!\n");
+ rcu_read_unlock();
+ return -EINVAL;
+}
+postcore_initcall(schedtune_init);
diff --git a/kernel/sched/tune.h b/kernel/sched/tune.h
new file mode 100644
index 000000000000..4f6441771e4c
--- /dev/null
+++ b/kernel/sched/tune.h
@@ -0,0 +1,55 @@
+
+#ifdef CONFIG_SCHED_TUNE
+
+#include <linux/reciprocal_div.h>
+
+/*
+ * System energy normalization constants
+ */
+struct target_nrg {
+ unsigned long min_power;
+ unsigned long max_power;
+ struct reciprocal_value rdiv;
+};
+
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+
+int schedtune_cpu_boost(int cpu);
+int schedtune_task_boost(struct task_struct *tsk);
+
+int schedtune_prefer_idle(struct task_struct *tsk);
+
+void schedtune_exit_task(struct task_struct *tsk);
+
+void schedtune_enqueue_task(struct task_struct *p, int cpu);
+void schedtune_dequeue_task(struct task_struct *p, int cpu);
+
+#else /* CONFIG_CGROUP_SCHEDTUNE */
+
+#define schedtune_cpu_boost(cpu) get_sysctl_sched_cfs_boost()
+#define schedtune_task_boost(tsk) get_sysctl_sched_cfs_boost()
+
+#define schedtune_exit_task(task) do { } while (0)
+
+#define schedtune_enqueue_task(task, cpu) do { } while (0)
+#define schedtune_dequeue_task(task, cpu) do { } while (0)
+
+#endif /* CONFIG_CGROUP_SCHEDTUNE */
+
+int schedtune_normalize_energy(int energy);
+int schedtune_accept_deltas(int nrg_delta, int cap_delta,
+ struct task_struct *task);
+
+#else /* CONFIG_SCHED_TUNE */
+
+#define schedtune_cpu_boost(cpu) 0
+#define schedtune_task_boost(tsk) 0
+
+#define schedtune_exit_task(task) do { } while (0)
+
+#define schedtune_enqueue_task(task, cpu) do { } while (0)
+#define schedtune_dequeue_task(task, cpu) do { } while (0)
+
+#define schedtune_accept_deltas(nrg_delta, cap_delta, task) nrg_delta
+
+#endif /* CONFIG_SCHED_TUNE */
diff --git a/kernel/sched/walt.c b/kernel/sched/walt.c
new file mode 100644
index 000000000000..8d25ffbe4fed
--- /dev/null
+++ b/kernel/sched/walt.c
@@ -0,0 +1,900 @@
+/*
+ * Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ *
+ * Window Assisted Load Tracking (WALT) implementation credits:
+ * Srivatsa Vaddagiri, Steve Muckle, Syed Rameez Mustafa, Joonwoo Park,
+ * Pavan Kumar Kondeti, Olav Haugan
+ *
+ * 2016-03-06: Integration with EAS/refactoring by Vikram Mulukutla
+ * and Todd Kjos
+ */
+
+#include <linux/syscore_ops.h>
+#include <trace/events/sched.h>
+#include "sched.h"
+#include "walt.h"
+
+#define WINDOW_STATS_RECENT 0
+#define WINDOW_STATS_MAX 1
+#define WINDOW_STATS_MAX_RECENT_AVG 2
+#define WINDOW_STATS_AVG 3
+#define WINDOW_STATS_INVALID_POLICY 4
+
+#define EXITING_TASK_MARKER 0xdeaddead
+
+static __read_mostly unsigned int walt_ravg_hist_size = 5;
+static __read_mostly unsigned int walt_window_stats_policy =
+ WINDOW_STATS_MAX_RECENT_AVG;
+static __read_mostly unsigned int walt_account_wait_time = 1;
+static __read_mostly unsigned int walt_freq_account_wait_time = 0;
+static __read_mostly unsigned int walt_io_is_busy = 0;
+
+unsigned int sysctl_sched_walt_init_task_load_pct = 15;
+
+/* true -> use PELT based load stats, false -> use window-based load stats */
+bool __read_mostly walt_disabled = false;
+
+/*
+ * Window size (in ns). Adjust for the tick size so that the window
+ * rollover occurs just before the tick boundary.
+ */
+__read_mostly unsigned int walt_ravg_window =
+ (20000000 / TICK_NSEC) * TICK_NSEC;
+#define MIN_SCHED_RAVG_WINDOW ((10000000 / TICK_NSEC) * TICK_NSEC)
+#define MAX_SCHED_RAVG_WINDOW ((1000000000 / TICK_NSEC) * TICK_NSEC)
+
+static unsigned int sync_cpu;
+static ktime_t ktime_last;
+static bool walt_ktime_suspended;
+
+static unsigned int task_load(struct task_struct *p)
+{
+ return p->ravg.demand;
+}
+
+static inline void fixup_cum_window_demand(struct rq *rq, s64 delta)
+{
+ rq->cum_window_demand += delta;
+ if (unlikely((s64)rq->cum_window_demand < 0))
+ rq->cum_window_demand = 0;
+}
+
+void
+walt_inc_cumulative_runnable_avg(struct rq *rq,
+ struct task_struct *p)
+{
+ rq->cumulative_runnable_avg += p->ravg.demand;
+
+ /*
+ * Add a task's contribution to the cumulative window demand when
+ *
+ * (1) task is enqueued with on_rq = 1 i.e migration,
+ * prio/cgroup/class change.
+ * (2) task is waking for the first time in this window.
+ */
+ if (p->on_rq || (p->last_sleep_ts < rq->window_start))
+ fixup_cum_window_demand(rq, p->ravg.demand);
+}
+
+void
+walt_dec_cumulative_runnable_avg(struct rq *rq,
+ struct task_struct *p)
+{
+ rq->cumulative_runnable_avg -= p->ravg.demand;
+ BUG_ON((s64)rq->cumulative_runnable_avg < 0);
+
+ /*
+ * on_rq will be 1 for sleeping tasks. So check if the task
+ * is migrating or dequeuing in RUNNING state to change the
+ * prio/cgroup/class.
+ */
+ if (task_on_rq_migrating(p) || p->state == TASK_RUNNING)
+ fixup_cum_window_demand(rq, -(s64)p->ravg.demand);
+}
+
+static void
+fixup_cumulative_runnable_avg(struct rq *rq,
+ struct task_struct *p, u64 new_task_load)
+{
+ s64 task_load_delta = (s64)new_task_load - task_load(p);
+
+ rq->cumulative_runnable_avg += task_load_delta;
+ if ((s64)rq->cumulative_runnable_avg < 0)
+ panic("cra less than zero: tld: %lld, task_load(p) = %u\n",
+ task_load_delta, task_load(p));
+
+ fixup_cum_window_demand(rq, task_load_delta);
+}
+
+u64 walt_ktime_clock(void)
+{
+ if (unlikely(walt_ktime_suspended))
+ return ktime_to_ns(ktime_last);
+ return ktime_get_ns();
+}
+
+static void walt_resume(void)
+{
+ walt_ktime_suspended = false;
+}
+
+static int walt_suspend(void)
+{
+ ktime_last = ktime_get();
+ walt_ktime_suspended = true;
+ return 0;
+}
+
+static struct syscore_ops walt_syscore_ops = {
+ .resume = walt_resume,
+ .suspend = walt_suspend
+};
+
+static int __init walt_init_ops(void)
+{
+ register_syscore_ops(&walt_syscore_ops);
+ return 0;
+}
+late_initcall(walt_init_ops);
+
+void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *cfs_rq,
+ struct task_struct *p)
+{
+ cfs_rq->cumulative_runnable_avg += p->ravg.demand;
+}
+
+void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *cfs_rq,
+ struct task_struct *p)
+{
+ cfs_rq->cumulative_runnable_avg -= p->ravg.demand;
+}
+
+static int exiting_task(struct task_struct *p)
+{
+ if (p->flags & PF_EXITING) {
+ if (p->ravg.sum_history[0] != EXITING_TASK_MARKER) {
+ p->ravg.sum_history[0] = EXITING_TASK_MARKER;
+ }
+ return 1;
+ }
+ return 0;
+}
+
+static int __init set_walt_ravg_window(char *str)
+{
+ unsigned int adj_window;
+ bool no_walt = walt_disabled;
+
+ get_option(&str, &walt_ravg_window);
+
+ /* Adjust for CONFIG_HZ */
+ adj_window = (walt_ravg_window / TICK_NSEC) * TICK_NSEC;
+
+ /* Warn if we're a bit too far away from the expected window size */
+ WARN(adj_window < walt_ravg_window - NSEC_PER_MSEC,
+ "tick-adjusted window size %u, original was %u\n", adj_window,
+ walt_ravg_window);
+
+ walt_ravg_window = adj_window;
+
+ walt_disabled = walt_disabled ||
+ (walt_ravg_window < MIN_SCHED_RAVG_WINDOW ||
+ walt_ravg_window > MAX_SCHED_RAVG_WINDOW);
+
+ WARN(!no_walt && walt_disabled,
+ "invalid window size, disabling WALT\n");
+
+ return 0;
+}
+
+early_param("walt_ravg_window", set_walt_ravg_window);
+
+static void
+update_window_start(struct rq *rq, u64 wallclock)
+{
+ s64 delta;
+ int nr_windows;
+
+ delta = wallclock - rq->window_start;
+ /* If the MPM global timer is cleared, set delta as 0 to avoid kernel BUG happening */
+ if (delta < 0) {
+ delta = 0;
+ WARN_ONCE(1, "WALT wallclock appears to have gone backwards or reset\n");
+ }
+
+ if (delta < walt_ravg_window)
+ return;
+
+ nr_windows = div64_u64(delta, walt_ravg_window);
+ rq->window_start += (u64)nr_windows * (u64)walt_ravg_window;
+
+ rq->cum_window_demand = rq->cumulative_runnable_avg;
+}
+
+/*
+ * Translate absolute delta time accounted on a CPU
+ * to a scale where 1024 is the capacity of the most
+ * capable CPU running at FMAX
+ */
+static u64 scale_exec_time(u64 delta, struct rq *rq)
+{
+ unsigned long capcurr = capacity_curr_of(cpu_of(rq));
+
+ return (delta * capcurr) >> SCHED_CAPACITY_SHIFT;
+}
+
+static int cpu_is_waiting_on_io(struct rq *rq)
+{
+ if (!walt_io_is_busy)
+ return 0;
+
+ return atomic_read(&rq->nr_iowait);
+}
+
+void walt_account_irqtime(int cpu, struct task_struct *curr,
+ u64 delta, u64 wallclock)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags, nr_windows;
+ u64 cur_jiffies_ts;
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+
+ /*
+ * cputime (wallclock) uses sched_clock so use the same here for
+ * consistency.
+ */
+ delta += sched_clock() - wallclock;
+ cur_jiffies_ts = get_jiffies_64();
+
+ if (is_idle_task(curr))
+ walt_update_task_ravg(curr, rq, IRQ_UPDATE, walt_ktime_clock(),
+ delta);
+
+ nr_windows = cur_jiffies_ts - rq->irqload_ts;
+
+ if (nr_windows) {
+ if (nr_windows < 10) {
+ /* Decay CPU's irqload by 3/4 for each window. */
+ rq->avg_irqload *= (3 * nr_windows);
+ rq->avg_irqload = div64_u64(rq->avg_irqload,
+ 4 * nr_windows);
+ } else {
+ rq->avg_irqload = 0;
+ }
+ rq->avg_irqload += rq->cur_irqload;
+ rq->cur_irqload = 0;
+ }
+
+ rq->cur_irqload += delta;
+ rq->irqload_ts = cur_jiffies_ts;
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+
+#define WALT_HIGH_IRQ_TIMEOUT 3
+
+u64 walt_irqload(int cpu) {
+ struct rq *rq = cpu_rq(cpu);
+ s64 delta;
+ delta = get_jiffies_64() - rq->irqload_ts;
+
+ /*
+ * Current context can be preempted by irq and rq->irqload_ts can be
+ * updated by irq context so that delta can be negative.
+ * But this is okay and we can safely return as this means there
+ * was recent irq occurrence.
+ */
+
+ if (delta < WALT_HIGH_IRQ_TIMEOUT)
+ return rq->avg_irqload;
+ else
+ return 0;
+}
+
+int walt_cpu_high_irqload(int cpu) {
+ return walt_irqload(cpu) >= sysctl_sched_walt_cpu_high_irqload;
+}
+
+static int account_busy_for_cpu_time(struct rq *rq, struct task_struct *p,
+ u64 irqtime, int event)
+{
+ if (is_idle_task(p)) {
+ /* TASK_WAKE && TASK_MIGRATE is not possible on idle task! */
+ if (event == PICK_NEXT_TASK)
+ return 0;
+
+ /* PUT_PREV_TASK, TASK_UPDATE && IRQ_UPDATE are left */
+ return irqtime || cpu_is_waiting_on_io(rq);
+ }
+
+ if (event == TASK_WAKE)
+ return 0;
+
+ if (event == PUT_PREV_TASK || event == IRQ_UPDATE ||
+ event == TASK_UPDATE)
+ return 1;
+
+ /* Only TASK_MIGRATE && PICK_NEXT_TASK left */
+ return walt_freq_account_wait_time;
+}
+
+/*
+ * Account cpu activity in its busy time counters (rq->curr/prev_runnable_sum)
+ */
+static void update_cpu_busy_time(struct task_struct *p, struct rq *rq,
+ int event, u64 wallclock, u64 irqtime)
+{
+ int new_window, nr_full_windows = 0;
+ int p_is_curr_task = (p == rq->curr);
+ u64 mark_start = p->ravg.mark_start;
+ u64 window_start = rq->window_start;
+ u32 window_size = walt_ravg_window;
+ u64 delta;
+
+ new_window = mark_start < window_start;
+ if (new_window) {
+ nr_full_windows = div64_u64((window_start - mark_start),
+ window_size);
+ if (p->ravg.active_windows < USHRT_MAX)
+ p->ravg.active_windows++;
+ }
+
+ /* Handle per-task window rollover. We don't care about the idle
+ * task or exiting tasks. */
+ if (new_window && !is_idle_task(p) && !exiting_task(p)) {
+ u32 curr_window = 0;
+
+ if (!nr_full_windows)
+ curr_window = p->ravg.curr_window;
+
+ p->ravg.prev_window = curr_window;
+ p->ravg.curr_window = 0;
+ }
+
+ if (!account_busy_for_cpu_time(rq, p, irqtime, event)) {
+ /* account_busy_for_cpu_time() = 0, so no update to the
+ * task's current window needs to be made. This could be
+ * for example
+ *
+ * - a wakeup event on a task within the current
+ * window (!new_window below, no action required),
+ * - switching to a new task from idle (PICK_NEXT_TASK)
+ * in a new window where irqtime is 0 and we aren't
+ * waiting on IO */
+
+ if (!new_window)
+ return;
+
+ /* A new window has started. The RQ demand must be rolled
+ * over if p is the current task. */
+ if (p_is_curr_task) {
+ u64 prev_sum = 0;
+
+ /* p is either idle task or an exiting task */
+ if (!nr_full_windows) {
+ prev_sum = rq->curr_runnable_sum;
+ }
+
+ rq->prev_runnable_sum = prev_sum;
+ rq->curr_runnable_sum = 0;
+ }
+
+ return;
+ }
+
+ if (!new_window) {
+ /* account_busy_for_cpu_time() = 1 so busy time needs
+ * to be accounted to the current window. No rollover
+ * since we didn't start a new window. An example of this is
+ * when a task starts execution and then sleeps within the
+ * same window. */
+
+ if (!irqtime || !is_idle_task(p) || cpu_is_waiting_on_io(rq))
+ delta = wallclock - mark_start;
+ else
+ delta = irqtime;
+ delta = scale_exec_time(delta, rq);
+ rq->curr_runnable_sum += delta;
+ if (!is_idle_task(p) && !exiting_task(p))
+ p->ravg.curr_window += delta;
+
+ return;
+ }
+
+ if (!p_is_curr_task) {
+ /* account_busy_for_cpu_time() = 1 so busy time needs
+ * to be accounted to the current window. A new window
+ * has also started, but p is not the current task, so the
+ * window is not rolled over - just split up and account
+ * as necessary into curr and prev. The window is only
+ * rolled over when a new window is processed for the current
+ * task.
+ *
+ * Irqtime can't be accounted by a task that isn't the
+ * currently running task. */
+
+ if (!nr_full_windows) {
+ /* A full window hasn't elapsed, account partial
+ * contribution to previous completed window. */
+ delta = scale_exec_time(window_start - mark_start, rq);
+ if (!exiting_task(p))
+ p->ravg.prev_window += delta;
+ } else {
+ /* Since at least one full window has elapsed,
+ * the contribution to the previous window is the
+ * full window (window_size). */
+ delta = scale_exec_time(window_size, rq);
+ if (!exiting_task(p))
+ p->ravg.prev_window = delta;
+ }
+ rq->prev_runnable_sum += delta;
+
+ /* Account piece of busy time in the current window. */
+ delta = scale_exec_time(wallclock - window_start, rq);
+ rq->curr_runnable_sum += delta;
+ if (!exiting_task(p))
+ p->ravg.curr_window = delta;
+
+ return;
+ }
+
+ if (!irqtime || !is_idle_task(p) || cpu_is_waiting_on_io(rq)) {
+ /* account_busy_for_cpu_time() = 1 so busy time needs
+ * to be accounted to the current window. A new window
+ * has started and p is the current task so rollover is
+ * needed. If any of these three above conditions are true
+ * then this busy time can't be accounted as irqtime.
+ *
+ * Busy time for the idle task or exiting tasks need not
+ * be accounted.
+ *
+ * An example of this would be a task that starts execution
+ * and then sleeps once a new window has begun. */
+
+ if (!nr_full_windows) {
+ /* A full window hasn't elapsed, account partial
+ * contribution to previous completed window. */
+ delta = scale_exec_time(window_start - mark_start, rq);
+ if (!is_idle_task(p) && !exiting_task(p))
+ p->ravg.prev_window += delta;
+
+ delta += rq->curr_runnable_sum;
+ } else {
+ /* Since at least one full window has elapsed,
+ * the contribution to the previous window is the
+ * full window (window_size). */
+ delta = scale_exec_time(window_size, rq);
+ if (!is_idle_task(p) && !exiting_task(p))
+ p->ravg.prev_window = delta;
+
+ }
+ /*
+ * Rollover for normal runnable sum is done here by overwriting
+ * the values in prev_runnable_sum and curr_runnable_sum.
+ * Rollover for new task runnable sum has completed by previous
+ * if-else statement.
+ */
+ rq->prev_runnable_sum = delta;
+
+ /* Account piece of busy time in the current window. */
+ delta = scale_exec_time(wallclock - window_start, rq);
+ rq->curr_runnable_sum = delta;
+ if (!is_idle_task(p) && !exiting_task(p))
+ p->ravg.curr_window = delta;
+
+ return;
+ }
+
+ if (irqtime) {
+ /* account_busy_for_cpu_time() = 1 so busy time needs
+ * to be accounted to the current window. A new window
+ * has started and p is the current task so rollover is
+ * needed. The current task must be the idle task because
+ * irqtime is not accounted for any other task.
+ *
+ * Irqtime will be accounted each time we process IRQ activity
+ * after a period of idleness, so we know the IRQ busy time
+ * started at wallclock - irqtime. */
+
+ BUG_ON(!is_idle_task(p));
+ mark_start = wallclock - irqtime;
+
+ /* Roll window over. If IRQ busy time was just in the current
+ * window then that is all that need be accounted. */
+ rq->prev_runnable_sum = rq->curr_runnable_sum;
+ if (mark_start > window_start) {
+ rq->curr_runnable_sum = scale_exec_time(irqtime, rq);
+ return;
+ }
+
+ /* The IRQ busy time spanned multiple windows. Process the
+ * busy time preceding the current window start first. */
+ delta = window_start - mark_start;
+ if (delta > window_size)
+ delta = window_size;
+ delta = scale_exec_time(delta, rq);
+ rq->prev_runnable_sum += delta;
+
+ /* Process the remaining IRQ busy time in the current window. */
+ delta = wallclock - window_start;
+ rq->curr_runnable_sum = scale_exec_time(delta, rq);
+
+ return;
+ }
+
+ BUG();
+}
+
+static int account_busy_for_task_demand(struct task_struct *p, int event)
+{
+ /* No need to bother updating task demand for exiting tasks
+ * or the idle task. */
+ if (exiting_task(p) || is_idle_task(p))
+ return 0;
+
+ /* When a task is waking up it is completing a segment of non-busy
+ * time. Likewise, if wait time is not treated as busy time, then
+ * when a task begins to run or is migrated, it is not running and
+ * is completing a segment of non-busy time. */
+ if (event == TASK_WAKE || (!walt_account_wait_time &&
+ (event == PICK_NEXT_TASK || event == TASK_MIGRATE)))
+ return 0;
+
+ return 1;
+}
+
+/*
+ * Called when new window is starting for a task, to record cpu usage over
+ * recently concluded window(s). Normally 'samples' should be 1. It can be > 1
+ * when, say, a real-time task runs without preemption for several windows at a
+ * stretch.
+ */
+static void update_history(struct rq *rq, struct task_struct *p,
+ u32 runtime, int samples, int event)
+{
+ u32 *hist = &p->ravg.sum_history[0];
+ int ridx, widx;
+ u32 max = 0, avg, demand;
+ u64 sum = 0;
+
+ /* Ignore windows where task had no activity */
+ if (!runtime || is_idle_task(p) || exiting_task(p) || !samples)
+ goto done;
+
+ /* Push new 'runtime' value onto stack */
+ widx = walt_ravg_hist_size - 1;
+ ridx = widx - samples;
+ for (; ridx >= 0; --widx, --ridx) {
+ hist[widx] = hist[ridx];
+ sum += hist[widx];
+ if (hist[widx] > max)
+ max = hist[widx];
+ }
+
+ for (widx = 0; widx < samples && widx < walt_ravg_hist_size; widx++) {
+ hist[widx] = runtime;
+ sum += hist[widx];
+ if (hist[widx] > max)
+ max = hist[widx];
+ }
+
+ p->ravg.sum = 0;
+
+ if (walt_window_stats_policy == WINDOW_STATS_RECENT) {
+ demand = runtime;
+ } else if (walt_window_stats_policy == WINDOW_STATS_MAX) {
+ demand = max;
+ } else {
+ avg = div64_u64(sum, walt_ravg_hist_size);
+ if (walt_window_stats_policy == WINDOW_STATS_AVG)
+ demand = avg;
+ else
+ demand = max(avg, runtime);
+ }
+
+ /*
+ * A throttled deadline sched class task gets dequeued without
+ * changing p->on_rq. Since the dequeue decrements hmp stats
+ * avoid decrementing it here again.
+ *
+ * When window is rolled over, the cumulative window demand
+ * is reset to the cumulative runnable average (contribution from
+ * the tasks on the runqueue). If the current task is dequeued
+ * already, it's demand is not included in the cumulative runnable
+ * average. So add the task demand separately to cumulative window
+ * demand.
+ */
+ if (!task_has_dl_policy(p) || !p->dl.dl_throttled) {
+ if (task_on_rq_queued(p))
+ fixup_cumulative_runnable_avg(rq, p, demand);
+ else if (rq->curr == p)
+ fixup_cum_window_demand(rq, demand);
+ }
+
+ p->ravg.demand = demand;
+
+done:
+ trace_walt_update_history(rq, p, runtime, samples, event);
+ return;
+}
+
+static void add_to_task_demand(struct rq *rq, struct task_struct *p,
+ u64 delta)
+{
+ delta = scale_exec_time(delta, rq);
+ p->ravg.sum += delta;
+ if (unlikely(p->ravg.sum > walt_ravg_window))
+ p->ravg.sum = walt_ravg_window;
+}
+
+/*
+ * Account cpu demand of task and/or update task's cpu demand history
+ *
+ * ms = p->ravg.mark_start;
+ * wc = wallclock
+ * ws = rq->window_start
+ *
+ * Three possibilities:
+ *
+ * a) Task event is contained within one window.
+ * window_start < mark_start < wallclock
+ *
+ * ws ms wc
+ * | | |
+ * V V V
+ * |---------------|
+ *
+ * In this case, p->ravg.sum is updated *iff* event is appropriate
+ * (ex: event == PUT_PREV_TASK)
+ *
+ * b) Task event spans two windows.
+ * mark_start < window_start < wallclock
+ *
+ * ms ws wc
+ * | | |
+ * V V V
+ * -----|-------------------
+ *
+ * In this case, p->ravg.sum is updated with (ws - ms) *iff* event
+ * is appropriate, then a new window sample is recorded followed
+ * by p->ravg.sum being set to (wc - ws) *iff* event is appropriate.
+ *
+ * c) Task event spans more than two windows.
+ *
+ * ms ws_tmp ws wc
+ * | | | |
+ * V V V V
+ * ---|-------|-------|-------|-------|------
+ * | |
+ * |<------ nr_full_windows ------>|
+ *
+ * In this case, p->ravg.sum is updated with (ws_tmp - ms) first *iff*
+ * event is appropriate, window sample of p->ravg.sum is recorded,
+ * 'nr_full_window' samples of window_size is also recorded *iff*
+ * event is appropriate and finally p->ravg.sum is set to (wc - ws)
+ * *iff* event is appropriate.
+ *
+ * IMPORTANT : Leave p->ravg.mark_start unchanged, as update_cpu_busy_time()
+ * depends on it!
+ */
+static void update_task_demand(struct task_struct *p, struct rq *rq,
+ int event, u64 wallclock)
+{
+ u64 mark_start = p->ravg.mark_start;
+ u64 delta, window_start = rq->window_start;
+ int new_window, nr_full_windows;
+ u32 window_size = walt_ravg_window;
+
+ new_window = mark_start < window_start;
+ if (!account_busy_for_task_demand(p, event)) {
+ if (new_window)
+ /* If the time accounted isn't being accounted as
+ * busy time, and a new window started, only the
+ * previous window need be closed out with the
+ * pre-existing demand. Multiple windows may have
+ * elapsed, but since empty windows are dropped,
+ * it is not necessary to account those. */
+ update_history(rq, p, p->ravg.sum, 1, event);
+ return;
+ }
+
+ if (!new_window) {
+ /* The simple case - busy time contained within the existing
+ * window. */
+ add_to_task_demand(rq, p, wallclock - mark_start);
+ return;
+ }
+
+ /* Busy time spans at least two windows. Temporarily rewind
+ * window_start to first window boundary after mark_start. */
+ delta = window_start - mark_start;
+ nr_full_windows = div64_u64(delta, window_size);
+ window_start -= (u64)nr_full_windows * (u64)window_size;
+
+ /* Process (window_start - mark_start) first */
+ add_to_task_demand(rq, p, window_start - mark_start);
+
+ /* Push new sample(s) into task's demand history */
+ update_history(rq, p, p->ravg.sum, 1, event);
+ if (nr_full_windows)
+ update_history(rq, p, scale_exec_time(window_size, rq),
+ nr_full_windows, event);
+
+ /* Roll window_start back to current to process any remainder
+ * in current window. */
+ window_start += (u64)nr_full_windows * (u64)window_size;
+
+ /* Process (wallclock - window_start) next */
+ mark_start = window_start;
+ add_to_task_demand(rq, p, wallclock - mark_start);
+}
+
+/* Reflect task activity on its demand and cpu's busy time statistics */
+void walt_update_task_ravg(struct task_struct *p, struct rq *rq,
+ int event, u64 wallclock, u64 irqtime)
+{
+ if (walt_disabled || !rq->window_start)
+ return;
+
+ lockdep_assert_held(&rq->lock);
+
+ update_window_start(rq, wallclock);
+
+ if (!p->ravg.mark_start)
+ goto done;
+
+ update_task_demand(p, rq, event, wallclock);
+ update_cpu_busy_time(p, rq, event, wallclock, irqtime);
+
+done:
+ trace_walt_update_task_ravg(p, rq, event, wallclock, irqtime);
+
+ p->ravg.mark_start = wallclock;
+}
+
+static void reset_task_stats(struct task_struct *p)
+{
+ u32 sum = 0;
+
+ if (exiting_task(p))
+ sum = EXITING_TASK_MARKER;
+
+ memset(&p->ravg, 0, sizeof(struct ravg));
+ /* Retain EXITING_TASK marker */
+ p->ravg.sum_history[0] = sum;
+}
+
+void walt_mark_task_starting(struct task_struct *p)
+{
+ u64 wallclock;
+ struct rq *rq = task_rq(p);
+
+ if (!rq->window_start) {
+ reset_task_stats(p);
+ return;
+ }
+
+ wallclock = walt_ktime_clock();
+ p->ravg.mark_start = wallclock;
+}
+
+void walt_set_window_start(struct rq *rq)
+{
+ int cpu = cpu_of(rq);
+ struct rq *sync_rq = cpu_rq(sync_cpu);
+
+ if (likely(rq->window_start))
+ return;
+
+ if (cpu == sync_cpu) {
+ rq->window_start = 1;
+ } else {
+ raw_spin_unlock(&rq->lock);
+ double_rq_lock(rq, sync_rq);
+ rq->window_start = cpu_rq(sync_cpu)->window_start;
+ rq->curr_runnable_sum = rq->prev_runnable_sum = 0;
+ raw_spin_unlock(&sync_rq->lock);
+ }
+
+ rq->curr->ravg.mark_start = rq->window_start;
+}
+
+void walt_migrate_sync_cpu(int cpu)
+{
+ if (cpu == sync_cpu)
+ sync_cpu = smp_processor_id();
+}
+
+void walt_fixup_busy_time(struct task_struct *p, int new_cpu)
+{
+ struct rq *src_rq = task_rq(p);
+ struct rq *dest_rq = cpu_rq(new_cpu);
+ u64 wallclock;
+
+ if (!p->on_rq && p->state != TASK_WAKING)
+ return;
+
+ if (exiting_task(p)) {
+ return;
+ }
+
+ if (p->state == TASK_WAKING)
+ double_rq_lock(src_rq, dest_rq);
+
+ wallclock = walt_ktime_clock();
+
+ walt_update_task_ravg(task_rq(p)->curr, task_rq(p),
+ TASK_UPDATE, wallclock, 0);
+ walt_update_task_ravg(dest_rq->curr, dest_rq,
+ TASK_UPDATE, wallclock, 0);
+
+ walt_update_task_ravg(p, task_rq(p), TASK_MIGRATE, wallclock, 0);
+
+ /*
+ * When a task is migrating during the wakeup, adjust
+ * the task's contribution towards cumulative window
+ * demand.
+ */
+ if (p->state == TASK_WAKING &&
+ p->last_sleep_ts >= src_rq->window_start) {
+ fixup_cum_window_demand(src_rq, -(s64)p->ravg.demand);
+ fixup_cum_window_demand(dest_rq, p->ravg.demand);
+ }
+
+ if (p->ravg.curr_window) {
+ src_rq->curr_runnable_sum -= p->ravg.curr_window;
+ dest_rq->curr_runnable_sum += p->ravg.curr_window;
+ }
+
+ if (p->ravg.prev_window) {
+ src_rq->prev_runnable_sum -= p->ravg.prev_window;
+ dest_rq->prev_runnable_sum += p->ravg.prev_window;
+ }
+
+ if ((s64)src_rq->prev_runnable_sum < 0) {
+ src_rq->prev_runnable_sum = 0;
+ WARN_ON(1);
+ }
+ if ((s64)src_rq->curr_runnable_sum < 0) {
+ src_rq->curr_runnable_sum = 0;
+ WARN_ON(1);
+ }
+
+ trace_walt_migration_update_sum(src_rq, p);
+ trace_walt_migration_update_sum(dest_rq, p);
+
+ if (p->state == TASK_WAKING)
+ double_rq_unlock(src_rq, dest_rq);
+}
+
+void walt_init_new_task_load(struct task_struct *p)
+{
+ int i;
+ u32 init_load_windows =
+ div64_u64((u64)sysctl_sched_walt_init_task_load_pct *
+ (u64)walt_ravg_window, 100);
+ u32 init_load_pct = current->init_load_pct;
+
+ p->init_load_pct = 0;
+ memset(&p->ravg, 0, sizeof(struct ravg));
+
+ if (init_load_pct) {
+ init_load_windows = div64_u64((u64)init_load_pct *
+ (u64)walt_ravg_window, 100);
+ }
+
+ p->ravg.demand = init_load_windows;
+ for (i = 0; i < RAVG_HIST_SIZE_MAX; ++i)
+ p->ravg.sum_history[i] = init_load_windows;
+}
diff --git a/kernel/sched/walt.h b/kernel/sched/walt.h
new file mode 100644
index 000000000000..de7edac43674
--- /dev/null
+++ b/kernel/sched/walt.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (c) 2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * 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.
+ */
+
+#ifndef __WALT_H
+#define __WALT_H
+
+#ifdef CONFIG_SCHED_WALT
+
+void walt_update_task_ravg(struct task_struct *p, struct rq *rq, int event,
+ u64 wallclock, u64 irqtime);
+void walt_inc_cumulative_runnable_avg(struct rq *rq, struct task_struct *p);
+void walt_dec_cumulative_runnable_avg(struct rq *rq, struct task_struct *p);
+void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *rq,
+ struct task_struct *p);
+void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *rq,
+ struct task_struct *p);
+void walt_fixup_busy_time(struct task_struct *p, int new_cpu);
+void walt_init_new_task_load(struct task_struct *p);
+void walt_mark_task_starting(struct task_struct *p);
+void walt_set_window_start(struct rq *rq);
+void walt_migrate_sync_cpu(int cpu);
+void walt_init_cpu_efficiency(void);
+u64 walt_ktime_clock(void);
+void walt_account_irqtime(int cpu, struct task_struct *curr, u64 delta,
+ u64 wallclock);
+
+u64 walt_irqload(int cpu);
+int walt_cpu_high_irqload(int cpu);
+
+#else /* CONFIG_SCHED_WALT */
+
+static inline void walt_update_task_ravg(struct task_struct *p, struct rq *rq,
+ int event, u64 wallclock, u64 irqtime) { }
+static inline void walt_inc_cumulative_runnable_avg(struct rq *rq, struct task_struct *p) { }
+static inline void walt_dec_cumulative_runnable_avg(struct rq *rq, struct task_struct *p) { }
+static inline void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *rq,
+ struct task_struct *p) { }
+static inline void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *rq,
+ struct task_struct *p) { }
+static inline void walt_fixup_busy_time(struct task_struct *p, int new_cpu) { }
+static inline void walt_init_new_task_load(struct task_struct *p) { }
+static inline void walt_mark_task_starting(struct task_struct *p) { }
+static inline void walt_set_window_start(struct rq *rq) { }
+static inline void walt_migrate_sync_cpu(int cpu) { }
+static inline void walt_init_cpu_efficiency(void) { }
+static inline u64 walt_ktime_clock(void) { return 0; }
+
+#define walt_cpu_high_irqload(cpu) false
+
+#endif /* CONFIG_SCHED_WALT */
+
+extern bool walt_disabled;
+
+#endif
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 15a1795bbba1..a39f81c7e87a 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -16,6 +16,8 @@
#include <linux/atomic.h>
#include <linux/audit.h>
#include <linux/compat.h>
+#include <linux/nospec.h>
+#include <linux/prctl.h>
#include <linux/sched.h>
#include <linux/seccomp.h>
#include <linux/slab.h>
@@ -173,7 +175,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
*
* Returns valid seccomp BPF response codes.
*/
-static u32 seccomp_run_filters(struct seccomp_data *sd)
+static u32 seccomp_run_filters(const struct seccomp_data *sd)
{
struct seccomp_data sd_local;
u32 ret = SECCOMP_RET_ALLOW;
@@ -214,8 +216,11 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
return true;
}
+void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { }
+
static inline void seccomp_assign_mode(struct task_struct *task,
- unsigned long seccomp_mode)
+ unsigned long seccomp_mode,
+ unsigned long flags)
{
assert_spin_locked(&task->sighand->siglock);
@@ -225,6 +230,9 @@ static inline void seccomp_assign_mode(struct task_struct *task,
* filter) is set.
*/
smp_mb__before_atomic();
+ /* Assume default seccomp processes want spec flaw mitigation. */
+ if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0)
+ arch_seccomp_spec_mitigate(task);
set_tsk_thread_flag(task, TIF_SECCOMP);
}
@@ -292,7 +300,7 @@ static inline pid_t seccomp_can_sync_threads(void)
* without dropping the locks.
*
*/
-static inline void seccomp_sync_threads(void)
+static inline void seccomp_sync_threads(unsigned long flags)
{
struct task_struct *thread, *caller;
@@ -333,7 +341,8 @@ static inline void seccomp_sync_threads(void)
* allow one thread to transition the other.
*/
if (thread->seccomp.mode == SECCOMP_MODE_DISABLED)
- seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+ seccomp_assign_mode(thread, SECCOMP_MODE_FILTER,
+ flags);
}
}
@@ -452,19 +461,24 @@ static long seccomp_attach_filter(unsigned int flags,
/* Now that the new filter is in place, synchronize to all threads. */
if (flags & SECCOMP_FILTER_FLAG_TSYNC)
- seccomp_sync_threads();
+ seccomp_sync_threads(flags);
return 0;
}
+void __get_seccomp_filter(struct seccomp_filter *filter)
+{
+ /* Reference count is bounded by the number of total processes. */
+ atomic_inc(&filter->usage);
+}
+
/* get_seccomp_filter - increments the reference count of the filter on @tsk */
void get_seccomp_filter(struct task_struct *tsk)
{
struct seccomp_filter *orig = tsk->seccomp.filter;
if (!orig)
return;
- /* Reference count is bounded by the number of total processes. */
- atomic_inc(&orig->usage);
+ __get_seccomp_filter(orig);
}
static inline void seccomp_filter_free(struct seccomp_filter *filter)
@@ -475,10 +489,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter)
}
}
-/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
-void put_seccomp_filter(struct task_struct *tsk)
+static void __put_seccomp_filter(struct seccomp_filter *orig)
{
- struct seccomp_filter *orig = tsk->seccomp.filter;
/* Clean up single-reference branches iteratively. */
while (orig && atomic_dec_and_test(&orig->usage)) {
struct seccomp_filter *freeme = orig;
@@ -487,6 +499,12 @@ void put_seccomp_filter(struct task_struct *tsk)
}
}
+/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
+void put_seccomp_filter(struct task_struct *tsk)
+{
+ __put_seccomp_filter(tsk->seccomp.filter);
+}
+
/**
* seccomp_send_sigsys - signals the task to allow in-process syscall emulation
* @syscall: syscall number to send to userland
@@ -561,20 +579,10 @@ void secure_computing_strict(int this_syscall)
BUG();
}
#else
-int __secure_computing(void)
-{
- u32 phase1_result = seccomp_phase1(NULL);
-
- if (likely(phase1_result == SECCOMP_PHASE1_OK))
- return 0;
- else if (likely(phase1_result == SECCOMP_PHASE1_SKIP))
- return -1;
- else
- return seccomp_phase2(phase1_result);
-}
#ifdef CONFIG_SECCOMP_FILTER
-static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
+static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
+ const bool recheck_after_trace)
{
u32 filter_ret, action;
int data;
@@ -606,10 +614,50 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
goto skip;
case SECCOMP_RET_TRACE:
- return filter_ret; /* Save the rest for phase 2. */
+ /* We've been put in this state by the ptracer already. */
+ if (recheck_after_trace)
+ return 0;
+
+ /* ENOSYS these calls if there is no tracer attached. */
+ if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
+ syscall_set_return_value(current,
+ task_pt_regs(current),
+ -ENOSYS, 0);
+ goto skip;
+ }
+
+ /* Allow the BPF to provide the event message */
+ ptrace_event(PTRACE_EVENT_SECCOMP, data);
+ /*
+ * The delivery of a fatal signal during event
+ * notification may silently skip tracer notification,
+ * which could leave us with a potentially unmodified
+ * syscall that the tracer would have liked to have
+ * changed. Since the process is about to die, we just
+ * force the syscall to be skipped and let the signal
+ * kill the process and correctly handle any tracer exit
+ * notifications.
+ */
+ if (fatal_signal_pending(current))
+ goto skip;
+ /* Check if the tracer forced the syscall to be skipped. */
+ this_syscall = syscall_get_nr(current, task_pt_regs(current));
+ if (this_syscall < 0)
+ goto skip;
+
+ /*
+ * Recheck the syscall, since it may have changed. This
+ * intentionally uses a NULL struct seccomp_data to force
+ * a reload of all registers. This does not goto skip since
+ * a skip would have already been reported.
+ */
+ if (__seccomp_filter(this_syscall, NULL, true))
+ return -1;
+
+ return 0;
case SECCOMP_RET_ALLOW:
- return SECCOMP_PHASE1_OK;
+ return 0;
case SECCOMP_RET_KILL:
default:
@@ -621,96 +669,38 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
skip:
audit_seccomp(this_syscall, 0, action);
- return SECCOMP_PHASE1_SKIP;
+ return -1;
+}
+#else
+static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
+ const bool recheck_after_trace)
+{
+ BUG();
}
#endif
-/**
- * seccomp_phase1() - run fast path seccomp checks on the current syscall
- * @arg sd: The seccomp_data or NULL
- *
- * This only reads pt_regs via the syscall_xyz helpers. The only change
- * it will make to pt_regs is via syscall_set_return_value, and it will
- * only do that if it returns SECCOMP_PHASE1_SKIP.
- *
- * If sd is provided, it will not read pt_regs at all.
- *
- * It may also call do_exit or force a signal; these actions must be
- * safe.
- *
- * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should
- * be processed normally.
- *
- * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be
- * invoked. In this case, seccomp_phase1 will have set the return value
- * using syscall_set_return_value.
- *
- * If it returns anything else, then the return value should be passed
- * to seccomp_phase2 from a context in which ptrace hooks are safe.
- */
-u32 seccomp_phase1(struct seccomp_data *sd)
+int __secure_computing(const struct seccomp_data *sd)
{
int mode = current->seccomp.mode;
- int this_syscall = sd ? sd->nr :
- syscall_get_nr(current, task_pt_regs(current));
+ int this_syscall;
if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
- return SECCOMP_PHASE1_OK;
+ return 0;
+
+ this_syscall = sd ? sd->nr :
+ syscall_get_nr(current, task_pt_regs(current));
switch (mode) {
case SECCOMP_MODE_STRICT:
__secure_computing_strict(this_syscall); /* may call do_exit */
- return SECCOMP_PHASE1_OK;
-#ifdef CONFIG_SECCOMP_FILTER
+ return 0;
case SECCOMP_MODE_FILTER:
- return __seccomp_phase1_filter(this_syscall, sd);
-#endif
+ return __seccomp_filter(this_syscall, sd, false);
default:
BUG();
}
}
-
-/**
- * seccomp_phase2() - finish slow path seccomp work for the current syscall
- * @phase1_result: The return value from seccomp_phase1()
- *
- * This must be called from a context in which ptrace hooks can be used.
- *
- * Returns 0 if the syscall should be processed or -1 to skip the syscall.
- */
-int seccomp_phase2(u32 phase1_result)
-{
- struct pt_regs *regs = task_pt_regs(current);
- u32 action = phase1_result & SECCOMP_RET_ACTION;
- int data = phase1_result & SECCOMP_RET_DATA;
-
- BUG_ON(action != SECCOMP_RET_TRACE);
-
- audit_seccomp(syscall_get_nr(current, regs), 0, action);
-
- /* Skip these calls if there is no tracer. */
- if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
- syscall_set_return_value(current, regs,
- -ENOSYS, 0);
- return -1;
- }
-
- /* Allow the BPF to provide the event message */
- ptrace_event(PTRACE_EVENT_SECCOMP, data);
- /*
- * The delivery of a fatal signal during event
- * notification may silently skip tracer notification.
- * Terminating the task now avoids executing a system
- * call that may not be intended.
- */
- if (fatal_signal_pending(current))
- do_exit(SIGSYS);
- if (syscall_get_nr(current, regs) < 0)
- return -1; /* Explicit request to skip. */
-
- return 0;
-}
#endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */
long prctl_get_seccomp(void)
@@ -738,7 +728,7 @@ static long seccomp_set_mode_strict(void)
#ifdef TIF_NOTSC
disable_TSC();
#endif
- seccomp_assign_mode(current, seccomp_mode);
+ seccomp_assign_mode(current, seccomp_mode, 0);
ret = 0;
out:
@@ -796,7 +786,7 @@ static long seccomp_set_mode_filter(unsigned int flags,
/* Do not free the successfully attached filter. */
prepared = NULL;
- seccomp_assign_mode(current, seccomp_mode);
+ seccomp_assign_mode(current, seccomp_mode, flags);
out:
spin_unlock_irq(&current->sighand->siglock);
if (flags & SECCOMP_FILTER_FLAG_TSYNC)
@@ -927,13 +917,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
if (!data)
goto out;
- get_seccomp_filter(task);
+ __get_seccomp_filter(filter);
spin_unlock_irq(&task->sighand->siglock);
if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog)))
ret = -EFAULT;
- put_seccomp_filter(task);
+ __put_seccomp_filter(filter);
return ret;
out:
diff --git a/kernel/signal.c b/kernel/signal.c
index f3f1f7a972fd..96e8c3cbfa38 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -72,7 +72,7 @@ static int sig_task_ignored(struct task_struct *t, int sig, bool force)
handler = sig_handler(t, sig);
if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) &&
- handler == SIG_DFL && !force)
+ handler == SIG_DFL && !(force && sig_kernel_only(sig)))
return 1;
return sig_handler_ignored(handler, sig);
@@ -88,13 +88,15 @@ static int sig_ignored(struct task_struct *t, int sig, bool force)
if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
return 0;
- if (!sig_task_ignored(t, sig, force))
- return 0;
-
/*
- * Tracers may want to know about even ignored signals.
+ * Tracers may want to know about even ignored signal unless it
+ * is SIGKILL which can't be reported anyway but can be ignored
+ * by SIGNAL_UNKILLABLE task.
*/
- return !t->ptrace;
+ if (t->ptrace && sig != SIGKILL)
+ return 0;
+
+ return sig_task_ignored(t, sig, force);
}
/*
@@ -346,7 +348,7 @@ static bool task_participate_group_stop(struct task_struct *task)
* fresh group stop. Read comment in do_signal_stop() for details.
*/
if (!sig->group_stop_count && !(sig->flags & SIGNAL_STOP_STOPPED)) {
- sig->flags = SIGNAL_STOP_STOPPED;
+ signal_set_stop_flags(sig, SIGNAL_STOP_STOPPED);
return true;
}
return false;
@@ -503,7 +505,8 @@ int unhandled_signal(struct task_struct *tsk, int sig)
return !tsk->ptrace;
}
-static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
+static void collect_signal(int sig, struct sigpending *list, siginfo_t *info,
+ bool *resched_timer)
{
struct sigqueue *q, *first = NULL;
@@ -525,6 +528,12 @@ static void collect_signal(int sig, struct sigpending *list, siginfo_t *info)
still_pending:
list_del_init(&first->list);
copy_siginfo(info, &first->info);
+
+ *resched_timer =
+ (first->flags & SIGQUEUE_PREALLOC) &&
+ (info->si_code == SI_TIMER) &&
+ (info->si_sys_private);
+
__sigqueue_free(first);
} else {
/*
@@ -541,12 +550,12 @@ still_pending:
}
static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
- siginfo_t *info)
+ siginfo_t *info, bool *resched_timer)
{
int sig = next_signal(pending, mask);
if (sig)
- collect_signal(sig, pending, info);
+ collect_signal(sig, pending, info, resched_timer);
return sig;
}
@@ -558,15 +567,16 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask,
*/
int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
+ bool resched_timer = false;
int signr;
/* We only dequeue private signals from ourselves, we don't let
* signalfd steal them
*/
- signr = __dequeue_signal(&tsk->pending, mask, info);
+ signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer);
if (!signr) {
signr = __dequeue_signal(&tsk->signal->shared_pending,
- mask, info);
+ mask, info, &resched_timer);
/*
* itimer signal ?
*
@@ -611,7 +621,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
*/
current->jobctl |= JOBCTL_STOP_DEQUEUED;
}
- if ((info->si_code & __SI_MASK) == __SI_TIMER && info->si_sys_private) {
+ if (resched_timer) {
/*
* Release the siglock to ensure proper locking order
* of timer locks outside of siglocks. Note, we leave
@@ -686,6 +696,48 @@ static inline bool si_fromuser(const struct siginfo *info)
(!is_si_special(info) && SI_FROMUSER(info));
}
+static int dequeue_synchronous_signal(siginfo_t *info)
+{
+ struct task_struct *tsk = current;
+ struct sigpending *pending = &tsk->pending;
+ struct sigqueue *q, *sync = NULL;
+
+ /*
+ * Might a synchronous signal be in the queue?
+ */
+ if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK))
+ return 0;
+
+ /*
+ * Return the first synchronous signal in the queue.
+ */
+ list_for_each_entry(q, &pending->list, list) {
+ /* Synchronous signals have a postive si_code */
+ if ((q->info.si_code > SI_USER) &&
+ (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) {
+ sync = q;
+ goto next;
+ }
+ }
+ return 0;
+next:
+ /*
+ * Check if there is another siginfo for the same signal.
+ */
+ list_for_each_entry_continue(q, &pending->list, list) {
+ if (q->info.si_signo == sync->info.si_signo)
+ goto still_pending;
+ }
+
+ sigdelset(&pending->signal, sync->info.si_signo);
+ recalc_sigpending();
+still_pending:
+ list_del_init(&sync->list);
+ copy_siginfo(info, &sync->info);
+ __sigqueue_free(sync);
+ return info->si_signo;
+}
+
/*
* called with RCU read lock from check_kill_permission()
*/
@@ -837,7 +889,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
* will take ->siglock, notice SIGNAL_CLD_MASK, and
* notify its parent. See get_signal_to_deliver().
*/
- signal->flags = why | SIGNAL_STOP_CONTINUED;
+ signal_set_stop_flags(signal, why | SIGNAL_STOP_CONTINUED);
signal->group_stop_count = 0;
signal->group_exit_code = 0;
}
@@ -909,9 +961,9 @@ static void complete_signal(int sig, struct task_struct *p, int group)
* then start taking the whole group down immediately.
*/
if (sig_fatal(p, sig) &&
- !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
+ !(signal->flags & SIGNAL_GROUP_EXIT) &&
!sigismember(&t->real_blocked, sig) &&
- (sig == SIGKILL || !t->ptrace)) {
+ (sig == SIGKILL || !p->ptrace)) {
/*
* This signal will be fatal to the whole group.
*/
@@ -981,7 +1033,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
result = TRACE_SIGNAL_IGNORED;
if (!prepare_signal(sig, t,
- from_ancestor_ns || (info == SEND_SIG_FORCED)))
+ from_ancestor_ns || (info == SEND_SIG_PRIV) || (info == SEND_SIG_FORCED)))
goto ret;
pending = group ? &t->signal->shared_pending : &t->pending;
@@ -1382,6 +1434,10 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
return ret;
}
+ /* -INT_MIN is undefined. Exclude this case to avoid a UBSAN warning */
+ if (pid == INT_MIN)
+ return -ESRCH;
+
read_lock(&tasklist_lock);
if (pid != -1) {
ret = __kill_pgrp_info(sig, info,
@@ -2184,6 +2240,14 @@ relock:
goto relock;
}
+ /* Has this task already been marked for death? */
+ if (signal_group_exit(signal)) {
+ ksig->info.si_signo = signr = SIGKILL;
+ sigdelset(&current->pending.signal, SIGKILL);
+ recalc_sigpending();
+ goto fatal;
+ }
+
for (;;) {
struct k_sigaction *ka;
@@ -2197,7 +2261,15 @@ relock:
goto relock;
}
- signr = dequeue_signal(current, &current->blocked, &ksig->info);
+ /*
+ * Signals generated by the execution of an instruction
+ * need to be delivered before any other pending signals
+ * so that the instruction pointer in the signal stack
+ * frame points to the faulting instruction.
+ */
+ signr = dequeue_synchronous_signal(&ksig->info);
+ if (!signr)
+ signr = dequeue_signal(current, &current->blocked, &ksig->info);
if (!signr)
break; /* will return 0 */
@@ -2279,6 +2351,7 @@ relock:
continue;
}
+ fatal:
spin_unlock_irq(&sighand->siglock);
/*
@@ -2485,6 +2558,13 @@ void __set_current_blocked(const sigset_t *newset)
{
struct task_struct *tsk = current;
+ /*
+ * In case the signal mask hasn't changed, there is nothing we need
+ * to do. The current->blocked shouldn't be modified by other task.
+ */
+ if (sigequalsets(&tsk->blocked, newset))
+ return;
+
spin_lock_irq(&tsk->sighand->siglock);
__set_task_blocked(tsk, newset);
spin_unlock_irq(&tsk->sighand->siglock);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 479e4436f787..359be4f39986 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -227,7 +227,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
static inline void lockdep_softirq_end(bool in_hardirq) { }
#endif
-asmlinkage __visible void __do_softirq(void)
+asmlinkage __visible void __softirq_entry __do_softirq(void)
{
unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
unsigned long old_flags = current->flags;
diff --git a/kernel/sys.c b/kernel/sys.c
index 78947de6f969..ede0c1f4b860 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -41,6 +41,8 @@
#include <linux/syscore_ops.h>
#include <linux/version.h>
#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/mempolicy.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
@@ -53,6 +55,8 @@
#include <linux/uidgid.h>
#include <linux/cred.h>
+#include <linux/nospec.h>
+
#include <linux/kmsg_dump.h>
/* Move somewhere else to avoid recompiling? */
#include <generated/utsrelease.h>
@@ -1140,18 +1144,19 @@ static int override_release(char __user *release, size_t len)
SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
{
- int errno = 0;
+ struct new_utsname tmp;
down_read(&uts_sem);
- if (copy_to_user(name, utsname(), sizeof *name))
- errno = -EFAULT;
+ memcpy(&tmp, utsname(), sizeof(tmp));
up_read(&uts_sem);
+ if (copy_to_user(name, &tmp, sizeof(tmp)))
+ return -EFAULT;
- if (!errno && override_release(name->release, sizeof(name->release)))
- errno = -EFAULT;
- if (!errno && override_architecture(name))
- errno = -EFAULT;
- return errno;
+ if (override_release(name->release, sizeof(name->release)))
+ return -EFAULT;
+ if (override_architecture(name))
+ return -EFAULT;
+ return 0;
}
#ifdef __ARCH_WANT_SYS_OLD_UNAME
@@ -1160,55 +1165,46 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
*/
SYSCALL_DEFINE1(uname, struct old_utsname __user *, name)
{
- int error = 0;
+ struct old_utsname tmp;
if (!name)
return -EFAULT;
down_read(&uts_sem);
- if (copy_to_user(name, utsname(), sizeof(*name)))
- error = -EFAULT;
+ memcpy(&tmp, utsname(), sizeof(tmp));
up_read(&uts_sem);
+ if (copy_to_user(name, &tmp, sizeof(tmp)))
+ return -EFAULT;
- if (!error && override_release(name->release, sizeof(name->release)))
- error = -EFAULT;
- if (!error && override_architecture(name))
- error = -EFAULT;
- return error;
+ if (override_release(name->release, sizeof(name->release)))
+ return -EFAULT;
+ if (override_architecture(name))
+ return -EFAULT;
+ return 0;
}
SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name)
{
- int error;
+ struct oldold_utsname tmp = {};
if (!name)
return -EFAULT;
- if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname)))
- return -EFAULT;
down_read(&uts_sem);
- error = __copy_to_user(&name->sysname, &utsname()->sysname,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->sysname + __OLD_UTS_LEN);
- error |= __copy_to_user(&name->nodename, &utsname()->nodename,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->nodename + __OLD_UTS_LEN);
- error |= __copy_to_user(&name->release, &utsname()->release,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->release + __OLD_UTS_LEN);
- error |= __copy_to_user(&name->version, &utsname()->version,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->version + __OLD_UTS_LEN);
- error |= __copy_to_user(&name->machine, &utsname()->machine,
- __OLD_UTS_LEN);
- error |= __put_user(0, name->machine + __OLD_UTS_LEN);
+ memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN);
+ memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN);
+ memcpy(&tmp.release, &utsname()->release, __OLD_UTS_LEN);
+ memcpy(&tmp.version, &utsname()->version, __OLD_UTS_LEN);
+ memcpy(&tmp.machine, &utsname()->machine, __OLD_UTS_LEN);
up_read(&uts_sem);
+ if (copy_to_user(name, &tmp, sizeof(tmp)))
+ return -EFAULT;
- if (!error && override_architecture(name))
- error = -EFAULT;
- if (!error && override_release(name->release, sizeof(name->release)))
- error = -EFAULT;
- return error ? -EFAULT : 0;
+ if (override_architecture(name))
+ return -EFAULT;
+ if (override_release(name->release, sizeof(name->release)))
+ return -EFAULT;
+ return 0;
}
#endif
@@ -1222,17 +1218,18 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
- down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
- struct new_utsname *u = utsname();
+ struct new_utsname *u;
+ down_write(&uts_sem);
+ u = utsname();
memcpy(u->nodename, tmp, len);
memset(u->nodename + len, 0, sizeof(u->nodename) - len);
errno = 0;
uts_proc_notify(UTS_PROC_HOSTNAME);
+ up_write(&uts_sem);
}
- up_write(&uts_sem);
return errno;
}
@@ -1240,8 +1237,9 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
SYSCALL_DEFINE2(gethostname, char __user *, name, int, len)
{
- int i, errno;
+ int i;
struct new_utsname *u;
+ char tmp[__NEW_UTS_LEN + 1];
if (len < 0)
return -EINVAL;
@@ -1250,11 +1248,11 @@ SYSCALL_DEFINE2(gethostname, char __user *, name, int, len)
i = 1 + strlen(u->nodename);
if (i > len)
i = len;
- errno = 0;
- if (copy_to_user(name, u->nodename, i))
- errno = -EFAULT;
+ memcpy(tmp, u->nodename, i);
up_read(&uts_sem);
- return errno;
+ if (copy_to_user(name, tmp, i))
+ return -EFAULT;
+ return 0;
}
#endif
@@ -1273,17 +1271,18 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
if (len < 0 || len > __NEW_UTS_LEN)
return -EINVAL;
- down_write(&uts_sem);
errno = -EFAULT;
if (!copy_from_user(tmp, name, len)) {
- struct new_utsname *u = utsname();
+ struct new_utsname *u;
+ down_write(&uts_sem);
+ u = utsname();
memcpy(u->domainname, tmp, len);
memset(u->domainname + len, 0, sizeof(u->domainname) - len);
errno = 0;
uts_proc_notify(UTS_PROC_DOMAINNAME);
+ up_write(&uts_sem);
}
- up_write(&uts_sem);
return errno;
}
@@ -1311,6 +1310,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
if (resource >= RLIM_NLIMITS)
return -EINVAL;
+ resource = array_index_nospec(resource, RLIM_NLIMITS);
task_lock(current->group_leader);
x = current->signal->rlim[resource];
task_unlock(current->group_leader);
@@ -2072,10 +2072,169 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
}
#endif
+#ifdef CONFIG_MMU
+static int prctl_update_vma_anon_name(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end,
+ const char __user *name_addr)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ int error = 0;
+ pgoff_t pgoff;
+
+ if (name_addr == vma_get_anon_name(vma)) {
+ *prev = vma;
+ goto out;
+ }
+
+ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+ *prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma,
+ vma->vm_file, pgoff, vma_policy(vma),
+ vma->vm_userfaultfd_ctx, name_addr);
+ if (*prev) {
+ vma = *prev;
+ goto success;
+ }
+
+ *prev = vma;
+
+ if (start != vma->vm_start) {
+ error = split_vma(mm, vma, start, 1);
+ if (error)
+ goto out;
+ }
+
+ if (end != vma->vm_end) {
+ error = split_vma(mm, vma, end, 0);
+ if (error)
+ goto out;
+ }
+
+success:
+ if (!vma->vm_file)
+ vma->anon_name = name_addr;
+
+out:
+ if (error == -ENOMEM)
+ error = -EAGAIN;
+ return error;
+}
+
+static int prctl_set_vma_anon_name(unsigned long start, unsigned long end,
+ unsigned long arg)
+{
+ unsigned long tmp;
+ struct vm_area_struct *vma, *prev;
+ int unmapped_error = 0;
+ int error = -EINVAL;
+
+ /*
+ * If the interval [start,end) covers some unmapped address
+ * ranges, just ignore them, but return -ENOMEM at the end.
+ * - this matches the handling in madvise.
+ */
+ vma = find_vma_prev(current->mm, start, &prev);
+ if (vma && start > vma->vm_start)
+ prev = vma;
+
+ for (;;) {
+ /* Still start < end. */
+ error = -ENOMEM;
+ if (!vma)
+ return error;
+
+ /* Here start < (end|vma->vm_end). */
+ if (start < vma->vm_start) {
+ unmapped_error = -ENOMEM;
+ start = vma->vm_start;
+ if (start >= end)
+ return error;
+ }
+
+ /* Here vma->vm_start <= start < (end|vma->vm_end) */
+ tmp = vma->vm_end;
+ if (end < tmp)
+ tmp = end;
+
+ /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
+ error = prctl_update_vma_anon_name(vma, &prev, start, tmp,
+ (const char __user *)arg);
+ if (error)
+ return error;
+ start = tmp;
+ if (prev && start < prev->vm_end)
+ start = prev->vm_end;
+ error = unmapped_error;
+ if (start >= end)
+ return error;
+ if (prev)
+ vma = prev->vm_next;
+ else /* madvise_remove dropped mmap_sem */
+ vma = find_vma(current->mm, start);
+ }
+}
+
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+ unsigned long len_in, unsigned long arg)
+{
+ struct mm_struct *mm = current->mm;
+ int error;
+ unsigned long len;
+ unsigned long end;
+
+ if (start & ~PAGE_MASK)
+ return -EINVAL;
+ len = (len_in + ~PAGE_MASK) & PAGE_MASK;
+
+ /* Check to see whether len was rounded up from small -ve to zero */
+ if (len_in && !len)
+ return -EINVAL;
+
+ end = start + len;
+ if (end < start)
+ return -EINVAL;
+
+ if (end == start)
+ return 0;
+
+ down_write(&mm->mmap_sem);
+
+ switch (opt) {
+ case PR_SET_VMA_ANON_NAME:
+ error = prctl_set_vma_anon_name(start, end, arg);
+ break;
+ default:
+ error = -EINVAL;
+ }
+
+ up_write(&mm->mmap_sem);
+
+ return error;
+}
+#else /* CONFIG_MMU */
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+ unsigned long len_in, unsigned long arg)
+{
+ return -EINVAL;
+}
+#endif
+
+int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which)
+{
+ return -EINVAL;
+}
+
+int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
+ unsigned long ctrl)
+{
+ return -EINVAL;
+}
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
struct task_struct *me = current;
+ struct task_struct *tsk;
unsigned char comm[sizeof(me->comm)];
long error;
@@ -2169,7 +2328,10 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = perf_event_task_enable();
break;
case PR_GET_TIMERSLACK:
- error = current->timer_slack_ns;
+ if (current->timer_slack_ns > ULONG_MAX)
+ error = ULONG_MAX;
+ else
+ error = current->timer_slack_ns;
break;
case PR_SET_TIMERSLACK:
if (arg2 <= 0)
@@ -2218,6 +2380,26 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_GET_TID_ADDRESS:
error = prctl_get_tid_address(me, (int __user **)arg2);
break;
+ case PR_SET_TIMERSLACK_PID:
+ if (task_pid_vnr(current) != (pid_t)arg3 &&
+ !capable(CAP_SYS_NICE))
+ return -EPERM;
+ rcu_read_lock();
+ tsk = find_task_by_vpid((pid_t)arg3);
+ if (tsk == NULL) {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ if (arg2 <= 0)
+ tsk->timer_slack_ns =
+ tsk->default_timer_slack_ns;
+ else
+ tsk->timer_slack_ns = arg2;
+ put_task_struct(tsk);
+ error = 0;
+ break;
case PR_SET_CHILD_SUBREAPER:
me->signal->is_child_subreaper = !!arg2;
break;
@@ -2266,6 +2448,19 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_GET_FP_MODE:
error = GET_FP_MODE(me);
break;
+ case PR_SET_VMA:
+ error = prctl_set_vma(arg2, arg3, arg4, arg5);
+ break;
+ case PR_GET_SPECULATION_CTRL:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = arch_prctl_spec_ctrl_get(me, arg2);
+ break;
+ case PR_SET_SPECULATION_CTRL:
+ if (arg4 || arg5)
+ return -EINVAL;
+ error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
+ break;
default:
error = -EINVAL;
break;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 999e025bf68e..28df0358ba94 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -65,6 +65,7 @@
#include <linux/sched/sysctl.h>
#include <linux/kexec.h>
#include <linux/bpf.h>
+#include <linux/mount.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
@@ -104,6 +105,7 @@ extern char core_pattern[];
extern unsigned int core_pipe_limit;
#endif
extern int pid_max;
+extern int extra_free_kbytes;
extern int pid_max_min, pid_max_max;
extern int percpu_pagelist_fraction;
extern int compat_log;
@@ -124,7 +126,9 @@ static int zero;
static int __maybe_unused one = 1;
static int __maybe_unused two = 2;
static int __maybe_unused four = 4;
+static unsigned long zero_ul;
static unsigned long one_ul = 1;
+static unsigned long long_max = LONG_MAX;
static int one_hundred = 100;
#ifdef CONFIG_PRINTK
static int ten_thousand = 10000;
@@ -173,7 +177,7 @@ extern int no_unaligned_warning;
#define SYSCTL_WRITES_WARN 0
#define SYSCTL_WRITES_STRICT 1
-static int sysctl_writes_strict = SYSCTL_WRITES_WARN;
+static int sysctl_writes_strict = SYSCTL_WRITES_STRICT;
static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
@@ -304,6 +308,50 @@ static struct ctl_table kern_table[] = {
.extra2 = &max_sched_granularity_ns,
},
{
+ .procname = "sched_sync_hint_enable",
+ .data = &sysctl_sched_sync_hint_enable,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#ifdef CONFIG_SCHED_WALT
+ {
+ .procname = "sched_use_walt_cpu_util",
+ .data = &sysctl_sched_use_walt_cpu_util,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "sched_use_walt_task_util",
+ .data = &sysctl_sched_use_walt_task_util,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "sched_walt_init_task_load_pct",
+ .data = &sysctl_sched_walt_init_task_load_pct,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "sched_walt_cpu_high_irqload",
+ .data = &sysctl_sched_walt_cpu_high_irqload,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+#endif
+ {
+ .procname = "sched_cstate_aware",
+ .data = &sysctl_sched_cstate_aware,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "sched_wakeup_granularity_ns",
.data = &sysctl_sched_wakeup_granularity,
.maxlen = sizeof(unsigned int),
@@ -341,7 +389,8 @@ static struct ctl_table kern_table[] = {
.data = &sysctl_sched_time_avg,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "sched_shares_window_ns",
@@ -434,6 +483,21 @@ static struct ctl_table kern_table[] = {
.extra1 = &one,
},
#endif
+#ifdef CONFIG_SCHED_TUNE
+ {
+ .procname = "sched_cfs_boost",
+ .data = &sysctl_sched_cfs_boost,
+ .maxlen = sizeof(sysctl_sched_cfs_boost),
+#ifdef CONFIG_CGROUP_SCHEDTUNE
+ .mode = 0444,
+#else
+ .mode = 0644,
+#endif
+ .proc_handler = &sysctl_sched_cfs_boost_handler,
+ .extra1 = &zero,
+ .extra2 = &one_hundred,
+ },
+#endif
#ifdef CONFIG_PROVE_LOCKING
{
.procname = "prove_locking",
@@ -1158,6 +1222,8 @@ static struct ctl_table kern_table[] = {
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = timer_migration_handler,
+ .extra1 = &zero,
+ .extra2 = &one,
},
#endif
#ifdef CONFIG_BPF_SYSCALL
@@ -1393,6 +1459,14 @@ static struct ctl_table vm_table[] = {
.extra1 = &zero,
},
{
+ .procname = "extra_free_kbytes",
+ .data = &extra_free_kbytes,
+ .maxlen = sizeof(extra_free_kbytes),
+ .mode = 0644,
+ .proc_handler = min_free_kbytes_sysctl_handler,
+ .extra1 = &zero,
+ },
+ {
.procname = "percpu_pagelist_fraction",
.data = &percpu_pagelist_fraction,
.maxlen = sizeof(percpu_pagelist_fraction),
@@ -1568,6 +1642,28 @@ static struct ctl_table vm_table[] = {
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
+ {
+ .procname = "mmap_rnd_bits",
+ .data = &mmap_rnd_bits,
+ .maxlen = sizeof(mmap_rnd_bits),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&mmap_rnd_bits_min,
+ .extra2 = (void *)&mmap_rnd_bits_max,
+ },
+#endif
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
+ {
+ .procname = "mmap_rnd_compat_bits",
+ .data = &mmap_rnd_compat_bits,
+ .maxlen = sizeof(mmap_rnd_compat_bits),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (void *)&mmap_rnd_compat_bits_min,
+ .extra2 = (void *)&mmap_rnd_compat_bits_max,
+ },
+#endif
{ }
};
@@ -1599,6 +1695,8 @@ static struct ctl_table fs_table[] = {
.maxlen = sizeof(files_stat.max_files),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
+ .extra1 = &zero_ul,
+ .extra2 = &long_max,
},
{
.procname = "nr_open",
@@ -1712,6 +1810,24 @@ static struct ctl_table fs_table[] = {
.extra2 = &one,
},
{
+ .procname = "protected_fifos",
+ .data = &sysctl_protected_fifos,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &two,
+ },
+ {
+ .procname = "protected_regular",
+ .data = &sysctl_protected_regular,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &two,
+ },
+ {
.procname = "suid_dumpable",
.data = &suid_dumpable,
.maxlen = sizeof(int),
@@ -1749,6 +1865,14 @@ static struct ctl_table fs_table[] = {
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
+ {
+ .procname = "mount-max",
+ .data = &sysctl_mount_max,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ },
{ }
};
@@ -2058,9 +2182,12 @@ static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
if (write) {
if (*negp)
return -EINVAL;
+ if (*lvalp > UINT_MAX)
+ return -EINVAL;
*valp = *lvalp;
} else {
unsigned int val = *valp;
+ *negp = false;
*lvalp = (unsigned long)val;
}
return 0;
@@ -2273,7 +2400,16 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
{
struct do_proc_dointvec_minmax_conv_param *param = data;
if (write) {
- int val = *negp ? -*lvalp : *lvalp;
+ int val;
+ if (*negp) {
+ if (*lvalp > (unsigned long) INT_MAX + 1)
+ return -EINVAL;
+ val = -*lvalp;
+ } else {
+ if (*lvalp > (unsigned long) INT_MAX)
+ return -EINVAL;
+ val = *lvalp;
+ }
if ((param->min && *param->min > val) ||
(param->max && *param->max < val))
return -EINVAL;
@@ -2414,6 +2550,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
break;
if (neg)
continue;
+ val = convmul * val / convdiv;
if ((min && val < *min) || (max && val > *max))
continue;
*i = val;
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 7fbba635a549..e78480b81f8d 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -339,7 +339,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start)
{
struct alarm_base *base = &alarm_bases[alarm->type];
- start = ktime_add(start, base->gettime());
+ start = ktime_add_safe(start, base->gettime());
alarm_start(alarm, start);
}
EXPORT_SYMBOL_GPL(alarm_start_relative);
@@ -425,7 +425,7 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
overrun++;
}
- alarm->node.expires = ktime_add(alarm->node.expires, interval);
+ alarm->node.expires = ktime_add_safe(alarm->node.expires, interval);
return overrun;
}
EXPORT_SYMBOL_GPL(alarm_forward);
@@ -611,13 +611,22 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
/* start the timer */
timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
+
+ /*
+ * Rate limit to the tick as a hot fix to prevent DOS. Will be
+ * mopped up later.
+ */
+ if (timr->it.alarm.interval.tv64 &&
+ ktime_to_ns(timr->it.alarm.interval) < TICK_NSEC)
+ timr->it.alarm.interval = ktime_set(0, TICK_NSEC);
+
exp = timespec_to_ktime(new_setting->it_value);
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
ktime_t now;
now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
- exp = ktime_add(now, exp);
+ exp = ktime_add_safe(now, exp);
}
alarm_start(&timr->it.alarm.alarmtimer, exp);
@@ -764,7 +773,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
ktime_t now = alarm_bases[type].gettime();
- exp = ktime_add(now, exp);
+
+ exp = ktime_add_safe(now, exp);
}
if (alarmtimer_do_nsleep(&alarm, exp))
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 17f7bcff1e02..8d2e7074860b 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -312,7 +312,7 @@ EXPORT_SYMBOL_GPL(__ktime_divns);
*/
ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs)
{
- ktime_t res = ktime_add(lhs, rhs);
+ ktime_t res = ktime_add_unsafe(lhs, rhs);
/*
* We use KTIME_SEC_MAX here, the maximum timeout which we can
@@ -435,6 +435,7 @@ void destroy_hrtimer_on_stack(struct hrtimer *timer)
{
debug_object_free(timer, &hrtimer_debug_descr);
}
+EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack);
#else
static inline void debug_hrtimer_init(struct hrtimer *timer) { }
@@ -669,7 +670,9 @@ static void hrtimer_reprogram(struct hrtimer *timer,
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base)
{
base->expires_next.tv64 = KTIME_MAX;
+ base->hang_detected = 0;
base->hres_active = 0;
+ base->next_timer = NULL;
}
/*
@@ -984,7 +987,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim,
* relative (HRTIMER_MODE_REL)
*/
void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
- unsigned long delta_ns, const enum hrtimer_mode mode)
+ u64 delta_ns, const enum hrtimer_mode mode)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
@@ -1137,7 +1140,12 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
cpu_base = raw_cpu_ptr(&hrtimer_bases);
- if (clock_id == CLOCK_REALTIME && mode != HRTIMER_MODE_ABS)
+ /*
+ * POSIX magic: Relative CLOCK_REALTIME timers are not affected by
+ * clock modifications, so they needs to become CLOCK_MONOTONIC to
+ * ensure POSIX compliance.
+ */
+ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL)
clock_id = CLOCK_MONOTONIC;
base = hrtimer_clockid_to_base(clock_id);
@@ -1553,7 +1561,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
struct restart_block *restart;
struct hrtimer_sleeper t;
int ret = 0;
- unsigned long slack;
+ u64 slack;
slack = current->timer_slack_ns;
if (dl_task(current) || rt_task(current))
@@ -1615,6 +1623,7 @@ static void init_hrtimers_cpu(int cpu)
timerqueue_init_head(&cpu_base->clock_base[i].active);
}
+ cpu_base->active_bases = 0;
cpu_base->cpu = cpu;
hrtimer_init_hres(cpu_base);
}
@@ -1729,7 +1738,7 @@ void __init hrtimers_init(void)
* @clock: timer clock, CLOCK_MONOTONIC or CLOCK_REALTIME
*/
int __sched
-schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
+schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
const enum hrtimer_mode mode, int clock)
{
struct hrtimer_sleeper t;
@@ -1797,7 +1806,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta,
*
* Returns 0 when the timer has expired otherwise -EINTR
*/
-int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+int __sched schedule_hrtimeout_range(ktime_t *expires, u64 delta,
const enum hrtimer_mode mode)
{
return schedule_hrtimeout_range_clock(expires, delta, mode,
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 9cff0ab82b63..e24008c098c6 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -300,14 +300,17 @@ out:
static int pc_clock_gettime(clockid_t id, struct timespec *ts)
{
struct posix_clock_desc cd;
+ struct timespec64 ts64;
int err;
err = get_clock_desc(id, &cd);
if (err)
return err;
- if (cd.clk->ops.clock_gettime)
- err = cd.clk->ops.clock_gettime(cd.clk, ts);
+ if (cd.clk->ops.clock_gettime) {
+ err = cd.clk->ops.clock_gettime(cd.clk, &ts64);
+ *ts = timespec64_to_timespec(ts64);
+ }
else
err = -EOPNOTSUPP;
@@ -319,14 +322,17 @@ static int pc_clock_gettime(clockid_t id, struct timespec *ts)
static int pc_clock_getres(clockid_t id, struct timespec *ts)
{
struct posix_clock_desc cd;
+ struct timespec64 ts64;
int err;
err = get_clock_desc(id, &cd);
if (err)
return err;
- if (cd.clk->ops.clock_getres)
- err = cd.clk->ops.clock_getres(cd.clk, ts);
+ if (cd.clk->ops.clock_getres) {
+ err = cd.clk->ops.clock_getres(cd.clk, &ts64);
+ *ts = timespec64_to_timespec(ts64);
+ }
else
err = -EOPNOTSUPP;
@@ -337,6 +343,7 @@ static int pc_clock_getres(clockid_t id, struct timespec *ts)
static int pc_clock_settime(clockid_t id, const struct timespec *ts)
{
+ struct timespec64 ts64 = timespec_to_timespec64(*ts);
struct posix_clock_desc cd;
int err;
@@ -350,7 +357,7 @@ static int pc_clock_settime(clockid_t id, const struct timespec *ts)
}
if (cd.clk->ops.clock_settime)
- err = cd.clk->ops.clock_settime(cd.clk, ts);
+ err = cd.clk->ops.clock_settime(cd.clk, &ts64);
else
err = -EOPNOTSUPP;
out:
@@ -403,29 +410,36 @@ static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
{
clockid_t id = kit->it_clock;
struct posix_clock_desc cd;
+ struct itimerspec64 ts64;
if (get_clock_desc(id, &cd))
return;
- if (cd.clk->ops.timer_gettime)
- cd.clk->ops.timer_gettime(cd.clk, kit, ts);
-
+ if (cd.clk->ops.timer_gettime) {
+ cd.clk->ops.timer_gettime(cd.clk, kit, &ts64);
+ *ts = itimerspec64_to_itimerspec(&ts64);
+ }
put_clock_desc(&cd);
}
static int pc_timer_settime(struct k_itimer *kit, int flags,
struct itimerspec *ts, struct itimerspec *old)
{
+ struct itimerspec64 ts64 = itimerspec_to_itimerspec64(ts);
clockid_t id = kit->it_clock;
struct posix_clock_desc cd;
+ struct itimerspec64 old64;
int err;
err = get_clock_desc(id, &cd);
if (err)
return err;
- if (cd.clk->ops.timer_settime)
- err = cd.clk->ops.timer_settime(cd.clk, kit, flags, ts, old);
+ if (cd.clk->ops.timer_settime) {
+ err = cd.clk->ops.timer_settime(cd.clk, kit, flags, &ts64, &old64);
+ if (old)
+ *old = itimerspec64_to_itimerspec(&old64);
+ }
else
err = -EOPNOTSUPP;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 80016b329d94..8fc68e60c795 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -103,7 +103,7 @@ static void bump_cpu_timer(struct k_itimer *timer,
continue;
timer->it.cpu.expires += incr;
- timer->it_overrun += 1 << i;
+ timer->it_overrun += 1LL << i;
delta -= incr;
}
}
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index f2826c35e918..0e6ed2e7d066 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -355,6 +355,17 @@ static __init int init_posix_timers(void)
__initcall(init_posix_timers);
+/*
+ * The siginfo si_overrun field and the return value of timer_getoverrun(2)
+ * are of type int. Clamp the overrun value to INT_MAX
+ */
+static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+{
+ s64 sum = timr->it_overrun_last + (s64)baseval;
+
+ return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+}
+
static void schedule_next_timer(struct k_itimer *timr)
{
struct hrtimer *timer = &timr->it.real.timer;
@@ -362,12 +373,11 @@ static void schedule_next_timer(struct k_itimer *timr)
if (timr->it.real.interval.tv64 == 0)
return;
- timr->it_overrun += (unsigned int) hrtimer_forward(timer,
- timer->base->get_time(),
- timr->it.real.interval);
+ timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
+ timr->it.real.interval);
timr->it_overrun_last = timr->it_overrun;
- timr->it_overrun = -1;
+ timr->it_overrun = -1LL;
++timr->it_requeue_pending;
hrtimer_restart(timer);
}
@@ -396,7 +406,7 @@ void do_schedule_next_timer(struct siginfo *info)
else
schedule_next_timer(timr);
- info->si_overrun += timr->it_overrun_last;
+ info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
}
if (timr)
@@ -491,8 +501,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
now = ktime_add(now, kj);
}
#endif
- timr->it_overrun += (unsigned int)
- hrtimer_forward(timer, now,
+ timr->it_overrun += hrtimer_forward(timer, now,
timr->it.real.interval);
ret = HRTIMER_RESTART;
++timr->it_requeue_pending;
@@ -507,17 +516,22 @@ static struct pid *good_sigevent(sigevent_t * event)
{
struct task_struct *rtn = current->group_leader;
- if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
- (!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
- !same_thread_group(rtn, current) ||
- (event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_SIGNAL))
- return NULL;
-
- if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
- ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
+ switch (event->sigev_notify) {
+ case SIGEV_SIGNAL | SIGEV_THREAD_ID:
+ rtn = find_task_by_vpid(event->sigev_notify_thread_id);
+ if (!rtn || !same_thread_group(rtn, current))
+ return NULL;
+ /* FALLTHRU */
+ case SIGEV_SIGNAL:
+ case SIGEV_THREAD:
+ if (event->sigev_signo <= 0 || event->sigev_signo > SIGRTMAX)
+ return NULL;
+ /* FALLTHRU */
+ case SIGEV_NONE:
+ return task_pid(rtn);
+ default:
return NULL;
-
- return task_pid(rtn);
+ }
}
void posix_timers_register_clock(const clockid_t clock_id,
@@ -628,7 +642,7 @@ SYSCALL_DEFINE3(timer_create, const clockid_t, which_clock,
it_id_set = IT_ID_SET;
new_timer->it_id = (timer_t) new_timer_id;
new_timer->it_clock = which_clock;
- new_timer->it_overrun = -1;
+ new_timer->it_overrun = -1LL;
if (timer_event_spec) {
if (copy_from_user(&event, timer_event_spec, sizeof (event))) {
@@ -745,8 +759,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
/* interval timer ? */
if (iv.tv64)
cur_setting->it_interval = ktime_to_timespec(iv);
- else if (!hrtimer_active(timer) &&
- (timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
+ else if (!hrtimer_active(timer) && timr->it_sigev_notify != SIGEV_NONE)
return;
now = timer->base->get_time();
@@ -757,8 +770,8 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
* expiry is > now.
*/
if (iv.tv64 && (timr->it_requeue_pending & REQUEUE_PENDING ||
- (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE))
- timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv);
+ timr->it_sigev_notify == SIGEV_NONE))
+ timr->it_overrun += hrtimer_forward(timer, now, iv);
remaining = __hrtimer_expires_remaining_adjusted(timer, now);
/* Return 0 only, when the timer is expired and not pending */
@@ -767,7 +780,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
* A single shot SIGEV_NONE timer must return 0, when
* it is expired !
*/
- if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
+ if (timr->it_sigev_notify != SIGEV_NONE)
cur_setting->it_value.tv_nsec = 1;
} else
cur_setting->it_value = ktime_to_timespec(remaining);
@@ -820,7 +833,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
if (!timr)
return -EINVAL;
- overrun = timr->it_overrun_last;
+ overrun = timer_overrun_to_int(timr, 0);
unlock_timer(timr, flags);
return overrun;
@@ -865,7 +878,7 @@ common_timer_set(struct k_itimer *timr, int flags,
timr->it.real.interval = timespec_to_ktime(new_setting->it_interval);
/* SIGEV_NONE timers are not queued ! See common_timer_get */
- if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
+ if (timr->it_sigev_notify == SIGEV_NONE) {
/* Setup correct expiry time for relative timers */
if (mode == HRTIMER_MODE_REL) {
hrtimer_add_expires(timer, timer->base->get_time());
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index a26036d37a38..382b159d8592 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -205,6 +205,11 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
update_clock_read_data(&rd);
+ if (sched_clock_timer.function != NULL) {
+ /* update timeout for clock wrap */
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+ }
+
r = rate;
if (r >= 4000000) {
r /= 1000000;
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f6aae7977824..22d7454b387b 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -610,6 +610,14 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
now = ktime_get();
/* Find all expired events */
for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
+ /*
+ * Required for !SMP because for_each_cpu() reports
+ * unconditionally CPU0 as set on UP kernels.
+ */
+ if (!IS_ENABLED(CONFIG_SMP) &&
+ cpumask_empty(tick_broadcast_oneshot_mask))
+ break;
+
td = &per_cpu(tick_cpu_device, cpu);
if (td->evtdev->next_event.tv64 <= now.tv64) {
cpumask_set_cpu(cpu, tmpmask);
@@ -871,6 +879,9 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
int cpu = smp_processor_id();
+ if (!bc)
+ return;
+
/* Set it up only once ! */
if (bc->event_handler != tick_handle_oneshot_broadcast) {
int was_periodic = clockevent_state_periodic(bc);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 22c57e191a23..4cd1145ec260 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -568,6 +568,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}
+static inline bool local_timer_softirq_pending(void)
+{
+ return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
+}
+
static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
ktime_t now, int cpu)
{
@@ -584,8 +589,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
} while (read_seqretry(&jiffies_lock, seq));
ts->last_jiffies = basejiff;
- if (rcu_needs_cpu(basemono, &next_rcu) ||
- arch_needs_cpu() || irq_work_needs_cpu()) {
+ /*
+ * Keep the periodic tick, when RCU, architecture or irq_work
+ * requests it.
+ * Aside of that check whether the local timer softirq is
+ * pending. If so its a bad idea to call get_next_timer_interrupt()
+ * because there is an already expired timer, so it will request
+ * immeditate expiry, which rearms the hardware timer with a
+ * minimal delta which brings us back to this place
+ * immediately. Lather, rinse and repeat...
+ */
+ if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+ irq_work_needs_cpu() || local_timer_softirq_pending()) {
next_tick = basemono + TICK_NSEC;
} else {
/*
@@ -870,6 +885,18 @@ ktime_t tick_nohz_get_sleep_length(void)
return ts->sleep_length;
}
+/**
+ * tick_nohz_get_idle_calls - return the current idle calls counter value
+ *
+ * Called from the schedutil frequency scaling governor in scheduler context.
+ */
+unsigned long tick_nohz_get_idle_calls(void)
+{
+ struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
+
+ return ts->idle_calls;
+}
+
static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
{
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 86751c68e08d..de70ac1f84d0 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -28,6 +28,7 @@
*/
#include <linux/export.h>
+#include <linux/kernel.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/timekeeper_internal.h>
@@ -258,9 +259,10 @@ unsigned int jiffies_to_msecs(const unsigned long j)
return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
#else
# if BITS_PER_LONG == 32
- return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32;
+ return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >>
+ HZ_TO_MSEC_SHR32;
# else
- return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN;
+ return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
# endif
#endif
}
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4ff237dbc006..7d9067f1c056 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -39,7 +39,9 @@
static struct {
seqcount_t seq;
struct timekeeper timekeeper;
-} tk_core ____cacheline_aligned;
+} tk_core ____cacheline_aligned = {
+ .seq = SEQCNT_ZERO(tk_core.seq),
+};
static DEFINE_RAW_SPINLOCK(timekeeper_lock);
static struct timekeeper shadow_timekeeper;
@@ -70,6 +72,10 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift;
tk->xtime_sec++;
}
+ while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) {
+ tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
+ tk->raw_sec++;
+ }
}
static inline struct timespec64 tk_xtime(struct timekeeper *tk)
@@ -116,6 +122,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
tk->offs_boot = ktime_add(tk->offs_boot, delta);
}
+/*
+ * tk_clock_read - atomic clocksource read() helper
+ *
+ * This helper is necessary to use in the read paths because, while the
+ * seqlock ensures we don't return a bad value while structures are updated,
+ * it doesn't protect from potential crashes. There is the possibility that
+ * the tkr's clocksource may change between the read reference, and the
+ * clock reference passed to the read function. This can cause crashes if
+ * the wrong clocksource is passed to the wrong read function.
+ * This isn't necessary to use when holding the timekeeper_lock or doing
+ * a read of the fast-timekeeper tkrs (which is protected by its own locking
+ * and update logic).
+ */
+static inline u64 tk_clock_read(struct tk_read_base *tkr)
+{
+ struct clocksource *clock = READ_ONCE(tkr->clock);
+
+ return clock->read(clock);
+}
+
#ifdef CONFIG_DEBUG_TIMEKEEPING
#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */
@@ -173,7 +199,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
*/
do {
seq = read_seqcount_begin(&tk_core.seq);
- now = tkr->read(tkr->clock);
+ now = tk_clock_read(tkr);
last = tkr->cycle_last;
mask = tkr->mask;
max = tkr->clock->max_cycles;
@@ -207,7 +233,7 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
cycle_t cycle_now, delta;
/* read clocksource */
- cycle_now = tkr->read(tkr->clock);
+ cycle_now = tk_clock_read(tkr);
/* calculate the delta since the last update_wall_time */
delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
@@ -235,12 +261,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
old_clock = tk->tkr_mono.clock;
tk->tkr_mono.clock = clock;
- tk->tkr_mono.read = clock->read;
tk->tkr_mono.mask = clock->mask;
- tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock);
+ tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono);
tk->tkr_raw.clock = clock;
- tk->tkr_raw.read = clock->read;
tk->tkr_raw.mask = clock->mask;
tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last;
@@ -259,18 +283,19 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
/* Go back from cycles -> shifted ns */
tk->xtime_interval = (u64) interval * clock->mult;
tk->xtime_remainder = ntpinterval - tk->xtime_interval;
- tk->raw_interval =
- ((u64) interval * clock->mult) >> clock->shift;
+ tk->raw_interval = interval * clock->mult;
/* if changing clocks, convert xtime_nsec shift units */
if (old_clock) {
int shift_change = clock->shift - old_clock->shift;
- if (shift_change < 0)
+ if (shift_change < 0) {
tk->tkr_mono.xtime_nsec >>= -shift_change;
- else
+ tk->tkr_raw.xtime_nsec >>= -shift_change;
+ } else {
tk->tkr_mono.xtime_nsec <<= shift_change;
+ tk->tkr_raw.xtime_nsec <<= shift_change;
+ }
}
- tk->tkr_raw.xtime_nsec = 0;
tk->tkr_mono.shift = clock->shift;
tk->tkr_raw.shift = clock->shift;
@@ -298,17 +323,34 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
static inline u32 arch_gettimeoffset(void) { return 0; }
#endif
+static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr,
+ cycle_t delta)
+{
+ u64 nsec;
+
+ nsec = delta * tkr->mult + tkr->xtime_nsec;
+ nsec >>= tkr->shift;
+
+ /* If arch requires, add in get_arch_timeoffset() */
+ return nsec + arch_gettimeoffset();
+}
+
static inline s64 timekeeping_get_ns(struct tk_read_base *tkr)
{
cycle_t delta;
- s64 nsec;
delta = timekeeping_get_delta(tkr);
+ return timekeeping_delta_to_ns(tkr, delta);
+}
- nsec = (delta * tkr->mult + tkr->xtime_nsec) >> tkr->shift;
+static inline s64 timekeeping_cycles_to_ns(struct tk_read_base *tkr,
+ cycle_t cycles)
+{
+ cycle_t delta;
- /* If arch requires, add in get_arch_timeoffset() */
- return nsec + arch_gettimeoffset();
+ /* calculate the delta since the last update_wall_time */
+ delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask);
+ return timekeeping_delta_to_ns(tkr, delta);
}
/**
@@ -385,8 +427,11 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
tkr = tkf->base + (seq & 0x01);
now = ktime_to_ns(tkr->base);
- now += clocksource_delta(tkr->read(tkr->clock),
- tkr->cycle_last, tkr->mask);
+ now += timekeeping_delta_to_ns(tkr,
+ clocksource_delta(
+ tk_clock_read(tkr),
+ tkr->cycle_last,
+ tkr->mask));
} while (read_seqcount_retry(&tkf->seq, seq));
return now;
@@ -404,6 +449,35 @@ u64 ktime_get_raw_fast_ns(void)
}
EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns);
+/**
+ * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock.
+ *
+ * To keep it NMI safe since we're accessing from tracing, we're not using a
+ * separate timekeeper with updates to monotonic clock and boot offset
+ * protected with seqlocks. This has the following minor side effects:
+ *
+ * (1) Its possible that a timestamp be taken after the boot offset is updated
+ * but before the timekeeper is updated. If this happens, the new boot offset
+ * is added to the old timekeeping making the clock appear to update slightly
+ * earlier:
+ * CPU 0 CPU 1
+ * timekeeping_inject_sleeptime64()
+ * __timekeeping_inject_sleeptime(tk, delta);
+ * timestamp();
+ * timekeeping_update(tk, TK_CLEAR_NTP...);
+ *
+ * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be
+ * partially updated. Since the tk->offs_boot update is a rare event, this
+ * should be a rare occurrence which postprocessing should be able to handle.
+ */
+u64 notrace ktime_get_boot_fast_ns(void)
+{
+ struct timekeeper *tk = &tk_core.timekeeper;
+
+ return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot));
+}
+EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
+
/* Suspend-time cycles value for halted fast timekeeper. */
static cycle_t cycles_at_suspend;
@@ -412,6 +486,10 @@ static cycle_t dummy_clock_read(struct clocksource *cs)
return cycles_at_suspend;
}
+static struct clocksource dummy_clock = {
+ .read = dummy_clock_read,
+};
+
/**
* halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
* @tk: Timekeeper to snapshot.
@@ -428,13 +506,13 @@ static void halt_fast_timekeeper(struct timekeeper *tk)
struct tk_read_base *tkr = &tk->tkr_mono;
memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
- cycles_at_suspend = tkr->read(tkr->clock);
- tkr_dummy.read = dummy_clock_read;
+ cycles_at_suspend = tk_clock_read(tkr);
+ tkr_dummy.clock = &dummy_clock;
update_fast_timekeeper(&tkr_dummy, &tk_fast_mono);
tkr = &tk->tkr_raw;
memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
- tkr_dummy.read = dummy_clock_read;
+ tkr_dummy.clock = &dummy_clock;
update_fast_timekeeper(&tkr_dummy, &tk_fast_raw);
}
@@ -546,9 +624,6 @@ static inline void tk_update_ktime_data(struct timekeeper *tk)
nsec = (u32) tk->wall_to_monotonic.tv_nsec;
tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec);
- /* Update the monotonic raw base */
- tk->tkr_raw.base = timespec64_to_ktime(tk->raw_time);
-
/*
* The sum of the nanoseconds portions of xtime and
* wall_to_monotonic can be greater/equal one second. Take
@@ -558,6 +633,9 @@ static inline void tk_update_ktime_data(struct timekeeper *tk)
if (nsec >= NSEC_PER_SEC)
seconds++;
tk->ktime_sec = seconds;
+
+ /* Update the monotonic raw base */
+ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC);
}
/* must hold timekeeper_lock */
@@ -598,11 +676,9 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action)
*/
static void timekeeping_forward_now(struct timekeeper *tk)
{
- struct clocksource *clock = tk->tkr_mono.clock;
cycle_t cycle_now, delta;
- s64 nsec;
- cycle_now = tk->tkr_mono.read(clock);
+ cycle_now = tk_clock_read(&tk->tkr_mono);
delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
tk->tkr_mono.cycle_last = cycle_now;
tk->tkr_raw.cycle_last = cycle_now;
@@ -612,10 +688,13 @@ static void timekeeping_forward_now(struct timekeeper *tk)
/* If arch requires, add in get_arch_timeoffset() */
tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift;
- tk_normalize_xtime(tk);
- nsec = clocksource_cyc2ns(delta, tk->tkr_raw.mult, tk->tkr_raw.shift);
- timespec64_add_ns(&tk->raw_time, nsec);
+ tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult;
+
+ /* If arch requires, add in get_arch_timeoffset() */
+ tk->tkr_raw.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_raw.shift;
+
+ tk_normalize_xtime(tk);
}
/**
@@ -1109,19 +1188,18 @@ int timekeeping_notify(struct clocksource *clock)
void getrawmonotonic64(struct timespec64 *ts)
{
struct timekeeper *tk = &tk_core.timekeeper;
- struct timespec64 ts64;
unsigned long seq;
s64 nsecs;
do {
seq = read_seqcount_begin(&tk_core.seq);
+ ts->tv_sec = tk->raw_sec;
nsecs = timekeeping_get_ns(&tk->tkr_raw);
- ts64 = tk->raw_time;
} while (read_seqcount_retry(&tk_core.seq, seq));
- timespec64_add_ns(&ts64, nsecs);
- *ts = ts64;
+ ts->tv_nsec = 0;
+ timespec64_add_ns(ts, nsecs);
}
EXPORT_SYMBOL(getrawmonotonic64);
@@ -1245,8 +1323,7 @@ void __init timekeeping_init(void)
tk_setup_internals(tk, clock);
tk_set_xtime(tk, &now);
- tk->raw_time.tv_sec = 0;
- tk->raw_time.tv_nsec = 0;
+ tk->raw_sec = 0;
if (boot.tv_sec == 0 && boot.tv_nsec == 0)
boot = tk_xtime(tk);
@@ -1385,7 +1462,7 @@ void timekeeping_resume(void)
* The less preferred source will only be tried if there is no better
* usable source. The rtc part is handled separately in rtc core code.
*/
- cycle_now = tk->tkr_mono.read(clock);
+ cycle_now = tk_clock_read(&tk->tkr_mono);
if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
cycle_now > tk->tkr_mono.cycle_last) {
u64 num, max = ULLONG_MAX;
@@ -1726,7 +1803,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
unsigned int *clock_set)
{
cycle_t interval = tk->cycle_interval << shift;
- u64 raw_nsecs;
+ u64 snsec_per_sec;
/* If the offset is smaller than a shifted interval, do nothing */
if (offset < interval)
@@ -1741,14 +1818,12 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
*clock_set |= accumulate_nsecs_to_secs(tk);
/* Accumulate raw time */
- raw_nsecs = (u64)tk->raw_interval << shift;
- raw_nsecs += tk->raw_time.tv_nsec;
- if (raw_nsecs >= NSEC_PER_SEC) {
- u64 raw_secs = raw_nsecs;
- raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
- tk->raw_time.tv_sec += raw_secs;
+ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift;
+ snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
+ while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) {
+ tk->tkr_raw.xtime_nsec -= snsec_per_sec;
+ tk->raw_sec++;
}
- tk->raw_time.tv_nsec = raw_nsecs;
/* Accumulate error between NTP and clock interval */
tk->ntp_error += tk->ntp_tick << shift;
@@ -1780,7 +1855,7 @@ void update_wall_time(void)
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
offset = real_tk->cycle_interval;
#else
- offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock),
+ offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
#endif
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index bbc5d1114583..523fe1669d4c 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -127,7 +127,7 @@ int timer_migration_handler(struct ctl_table *table, int write,
int ret;
mutex_lock(&mutex);
- ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!ret && write)
timers_update_migration(false);
mutex_unlock(&mutex);
@@ -764,8 +764,15 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer,
__acquires(timer->base->lock)
{
for (;;) {
- u32 tf = timer->flags;
struct tvec_base *base;
+ u32 tf;
+
+ /*
+ * We need to use READ_ONCE() here, otherwise the compiler
+ * might re-read @tf between the check for TIMER_MIGRATING
+ * and spin_lock().
+ */
+ tf = READ_ONCE(timer->flags);
if (!(tf & TIMER_MIGRATING)) {
base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK);
@@ -1698,10 +1705,10 @@ EXPORT_SYMBOL(msleep_interruptible);
static void __sched do_usleep_range(unsigned long min, unsigned long max)
{
ktime_t kmin;
- unsigned long delta;
+ u64 delta;
kmin = ktime_set(0, min * NSEC_PER_USEC);
- delta = (max - min) * NSEC_PER_USEC;
+ delta = (u64)(max - min) * NSEC_PER_USEC;
schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL);
}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index ba7d8b288bb3..1407ed20ea93 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -16,6 +16,7 @@
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/kallsyms.h>
+#include <linux/nmi.h>
#include <asm/uaccess.h>
@@ -96,6 +97,9 @@ print_active_timers(struct seq_file *m, struct hrtimer_clock_base *base,
next_one:
i = 0;
+
+ touch_nmi_watchdog();
+
raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
curr = timerqueue_getnext(&base->active);
@@ -207,6 +211,8 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
{
struct clock_event_device *dev = td->evtdev;
+ touch_nmi_watchdog();
+
SEQ_printf(m, "Tick Device: mode: %d\n", td->mode);
if (cpu < 0)
SEQ_printf(m, "Broadcast device\n");
@@ -393,7 +399,7 @@ static int __init init_timer_list_procfs(void)
{
struct proc_dir_entry *pe;
- pe = proc_create("timer_list", 0444, NULL, &timer_list_fops);
+ pe = proc_create("timer_list", 0400, NULL, &timer_list_fops);
if (!pe)
return -ENOMEM;
return 0;
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
index 1adecb4b87c8..7e4d715f9c22 100644
--- a/kernel/time/timer_stats.c
+++ b/kernel/time/timer_stats.c
@@ -417,7 +417,7 @@ static int __init init_tstats_procfs(void)
{
struct proc_dir_entry *pe;
- pe = proc_create("timer_stats", 0644, NULL, &tstats_fops);
+ pe = proc_create("timer_stats", 0600, NULL, &tstats_fops);
if (!pe)
return -ENOMEM;
return 0;
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e45db6b0d878..006eefb6ede0 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -77,6 +77,9 @@ config EVENT_TRACING
select CONTEXT_SWITCH_TRACER
bool
+config GPU_TRACEPOINTS
+ bool
+
config CONTEXT_SWITCH_TRACER
bool
@@ -162,6 +165,17 @@ config FUNCTION_GRAPH_TRACER
address on the current task structure into a stack of calls.
+config PREEMPTIRQ_EVENTS
+ bool "Enable trace events for preempt and irq disable/enable"
+ select TRACE_IRQFLAGS
+ depends on DEBUG_PREEMPT || !PROVE_LOCKING
+ default n
+ help
+ Enable tracing of disable and enable events for preemption and irqs.
+ For tracing preempt disable/enable events, DEBUG_PREEMPT must be
+ enabled. For tracing irq disable/enable events, PROVE_LOCKING must
+ be disabled.
+
config IRQSOFF_TRACER
bool "Interrupts-off Latency Tracer"
default n
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 05ea5167e6bb..4b35fb97ae44 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_TRACING) += trace_stat.o
obj-$(CONFIG_TRACING) += trace_printk.o
obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
+obj-$(CONFIG_PREEMPTIRQ_EVENTS) += trace_irqsoff.o
obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
@@ -68,6 +69,7 @@ obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
endif
obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_GPU_TRACEPOINTS) += gpu-traces.o
obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index a990824c8604..210b8e726a97 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -57,7 +57,8 @@ static struct tracer_flags blk_tracer_flags = {
};
/* Global reference count of probes */
-static atomic_t blk_probes_ref = ATOMIC_INIT(0);
+static DEFINE_MUTEX(blk_probe_mutex);
+static int blk_probes_ref;
static void blk_register_tracepoints(void);
static void blk_unregister_tracepoints(void);
@@ -300,11 +301,26 @@ static void blk_trace_free(struct blk_trace *bt)
kfree(bt);
}
+static void get_probe_ref(void)
+{
+ mutex_lock(&blk_probe_mutex);
+ if (++blk_probes_ref == 1)
+ blk_register_tracepoints();
+ mutex_unlock(&blk_probe_mutex);
+}
+
+static void put_probe_ref(void)
+{
+ mutex_lock(&blk_probe_mutex);
+ if (!--blk_probes_ref)
+ blk_unregister_tracepoints();
+ mutex_unlock(&blk_probe_mutex);
+}
+
static void blk_trace_cleanup(struct blk_trace *bt)
{
blk_trace_free(bt);
- if (atomic_dec_and_test(&blk_probes_ref))
- blk_unregister_tracepoints();
+ put_probe_ref();
}
int blk_trace_remove(struct request_queue *q)
@@ -522,8 +538,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
if (cmpxchg(&q->blk_trace, NULL, bt))
goto err;
- if (atomic_inc_return(&blk_probes_ref) == 1)
- blk_register_tracepoints();
+ get_probe_ref();
return 0;
err:
@@ -1466,9 +1481,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
if (bt == NULL)
return -EINVAL;
- if (atomic_dec_and_test(&blk_probes_ref))
- blk_unregister_tracepoints();
-
+ put_probe_ref();
blk_trace_free(bt);
return 0;
}
@@ -1499,8 +1512,7 @@ static int blk_trace_setup_queue(struct request_queue *q,
if (cmpxchg(&q->blk_trace, NULL, bt))
goto free_bt;
- if (atomic_inc_return(&blk_probes_ref) == 1)
- blk_register_tracepoints();
+ get_probe_ref();
return 0;
free_bt:
@@ -1704,6 +1716,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
mutex_lock(&bdev->bd_mutex);
if (attr == &dev_attr_enable) {
+ if (!!value == !!q->blk_trace) {
+ ret = 0;
+ goto out_unlock_bdev;
+ }
if (value)
ret = blk_trace_setup_queue(q, bdev);
else
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4228fd3682c3..3dd40c736067 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -119,11 +119,13 @@ static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
i++;
} else if (fmt[i] == 'p' || fmt[i] == 's') {
mod[fmt_cnt]++;
- i++;
- if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
+ /* disallow any further format extensions */
+ if (fmt[i + 1] != 0 &&
+ !isspace(fmt[i + 1]) &&
+ !ispunct(fmt[i + 1]))
return -EINVAL;
fmt_cnt++;
- if (fmt[i - 1] == 's') {
+ if (fmt[i] == 's') {
if (str_seen)
/* allow only one '%s' per fmt string */
return -EINVAL;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3f743b147247..6380ec0453e0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -32,6 +32,7 @@
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/rcupdate.h>
+#include <linux/kprobes.h>
#include <trace/events/sched.h>
@@ -2667,13 +2668,14 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
if (!command || !ftrace_enabled) {
/*
- * If these are control ops, they still need their
- * per_cpu field freed. Since, function tracing is
+ * If these are dynamic or control ops, they still
+ * need their data freed. Since, function tracing is
* not currently active, we can just free them
* without synchronizing all CPUs.
*/
- if (ops->flags & FTRACE_OPS_FL_CONTROL)
- control_ops_free(ops);
+ if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL))
+ goto free_ops;
+
return 0;
}
@@ -2728,6 +2730,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
schedule_on_each_cpu(ftrace_sync);
+ free_ops:
arch_ftrace_trampoline_free(ops);
if (ops->flags & FTRACE_OPS_FL_CONTROL)
@@ -3535,7 +3538,7 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod)
int exclude_mod = 0;
int found = 0;
int ret;
- int clear_filter;
+ int clear_filter = 0;
if (func) {
func_g.type = filter_parse_regex(func, len, &func_g.search,
@@ -3677,23 +3680,24 @@ static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash)
ftrace_probe_registered = 1;
}
-static void __disable_ftrace_function_probe(void)
+static bool __disable_ftrace_function_probe(void)
{
int i;
if (!ftrace_probe_registered)
- return;
+ return false;
for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
struct hlist_head *hhd = &ftrace_func_hash[i];
if (hhd->first)
- return;
+ return false;
}
/* no more funcs left */
ftrace_shutdown(&trace_probe_ops, 0);
ftrace_probe_registered = 0;
+ return true;
}
@@ -3820,6 +3824,7 @@ static void
__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
void *data, int flags)
{
+ struct ftrace_ops_hash old_hash_ops;
struct ftrace_func_entry *rec_entry;
struct ftrace_func_probe *entry;
struct ftrace_func_probe *p;
@@ -3831,6 +3836,7 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
struct hlist_node *tmp;
char str[KSYM_SYMBOL_LEN];
int i, ret;
+ bool disabled;
if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
func_g.search = NULL;
@@ -3840,7 +3846,6 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
func_g.type = filter_parse_regex(glob, strlen(glob),
&func_g.search, &not);
func_g.len = strlen(func_g.search);
- func_g.search = glob;
/* we do not support '!' for function probes */
if (WARN_ON(not))
@@ -3849,6 +3854,10 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
mutex_lock(&trace_probe_ops.func_hash->regex_lock);
+ old_hash_ops.filter_hash = old_hash;
+ /* Probes only have filters */
+ old_hash_ops.notrace_hash = NULL;
+
hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
if (!hash)
/* Hmm, should report this somehow */
@@ -3886,12 +3895,17 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
}
}
mutex_lock(&ftrace_lock);
- __disable_ftrace_function_probe();
+ disabled = __disable_ftrace_function_probe();
/*
* Remove after the disable is called. Otherwise, if the last
* probe is removed, a null hash means *all enabled*.
*/
ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+ /* still need to update the function call sites */
+ if (ftrace_enabled && !disabled)
+ ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+ &old_hash_ops);
synchronize_sched();
if (!ret)
free_ftrace_hash_rcu(old_hash);
@@ -4301,9 +4315,6 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer);
-static unsigned long save_global_trampoline;
-static unsigned long save_global_flags;
-
static int __init set_graph_function(char *str)
{
strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -4757,6 +4768,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops)
if (ops->flags & FTRACE_OPS_FL_ENABLED)
ftrace_shutdown(ops, 0);
ops->flags |= FTRACE_OPS_FL_DELETED;
+ ftrace_free_filter(ops);
mutex_unlock(&ftrace_lock);
}
@@ -5154,7 +5166,7 @@ static struct ftrace_ops control_ops = {
INIT_OPS_HASH(control_ops)
};
-static inline void
+static nokprobe_inline void
__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ignored, struct pt_regs *regs)
{
@@ -5203,11 +5215,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
{
__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
}
+NOKPROBE_SYMBOL(ftrace_ops_list_func);
#else
static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
{
__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
}
+NOKPROBE_SYMBOL(ftrace_ops_no_ops);
#endif
/*
@@ -5228,6 +5242,7 @@ static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip,
trace_clear_recursion(bit);
}
+NOKPROBE_SYMBOL(ftrace_ops_recurs_func);
/**
* ftrace_ops_get_func - get the function a trampoline should call
@@ -5893,17 +5908,6 @@ void unregister_ftrace_graph(void)
unregister_pm_notifier(&ftrace_suspend_notifier);
unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
-#ifdef CONFIG_DYNAMIC_FTRACE
- /*
- * Function graph does not allocate the trampoline, but
- * other global_ops do. We need to reset the ALLOC_TRAMP flag
- * if one was used.
- */
- global_ops.trampoline = save_global_trampoline;
- if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP)
- global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
-#endif
-
out:
mutex_unlock(&ftrace_lock);
}
diff --git a/kernel/trace/gpu-traces.c b/kernel/trace/gpu-traces.c
new file mode 100644
index 000000000000..a4b3f00faee3
--- /dev/null
+++ b/kernel/trace/gpu-traces.c
@@ -0,0 +1,23 @@
+/*
+ * GPU tracepoints
+ *
+ * Copyright (C) 2013 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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.
+ *
+ */
+
+#include <linux/module.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/gpu.h>
+
+EXPORT_TRACEPOINT_SYMBOL(gpu_sched_switch);
+EXPORT_TRACEPOINT_SYMBOL(gpu_job_enqueue);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index acbb0e73d3a2..1cf2402c6922 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
/* Missed count stored at end */
#define RB_MISSED_STORED (1 << 30)
+#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED)
+
struct buffer_data_page {
u64 time_stamp; /* page time stamp */
local_t commit; /* write committed index */
@@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
*/
size_t ring_buffer_page_len(void *page)
{
- return local_read(&((struct buffer_data_page *)page)->commit)
+ struct buffer_data_page *bpage = page;
+
+ return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
+ BUF_PAGE_HDR_SIZE;
}
@@ -697,7 +701,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
preempt_disable_notrace();
time = rb_time_stamp(buffer);
- preempt_enable_no_resched_notrace();
+ preempt_enable_notrace();
return time;
}
@@ -1509,6 +1513,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
tmp_iter_page = first_page;
do {
+ cond_resched();
+
to_remove_page = tmp_iter_page;
rb_inc_page(cpu_buffer, &tmp_iter_page);
@@ -3138,6 +3144,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
}
/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
+/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
* @cpu: The CPU buffer to stop
@@ -3440,11 +3462,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
{
struct ring_buffer_per_cpu *cpu_buffer;
+ struct buffer_page *reader;
+ struct buffer_page *head_page;
+ struct buffer_page *commit_page;
+ unsigned commit;
cpu_buffer = iter->cpu_buffer;
- return iter->head_page == cpu_buffer->commit_page &&
- iter->head == rb_commit_index(cpu_buffer);
+ /* Remember, trace recording is off when iterator is in use */
+ reader = cpu_buffer->reader_page;
+ head_page = cpu_buffer->head_page;
+ commit_page = cpu_buffer->commit_page;
+ commit = rb_page_commit(commit_page);
+
+ return ((iter->head_page == commit_page && iter->head == commit) ||
+ (iter->head_page == reader && commit_page == head_page &&
+ head_page->read == commit &&
+ iter->head == rb_page_commit(cpu_buffer->reader_page)));
}
EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
@@ -4008,6 +4042,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume);
* ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
* @buffer: The ring buffer to read from
* @cpu: The cpu buffer to iterate over
+ * @flags: gfp flags to use for memory allocation
*
* This performs the initial preparations necessary to iterate
* through the buffer. Memory is allocated, buffer recording
@@ -4025,7 +4060,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume);
* This overall must be paired with ring_buffer_read_finish.
*/
struct ring_buffer_iter *
-ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
+ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu, gfp_t flags)
{
struct ring_buffer_per_cpu *cpu_buffer;
struct ring_buffer_iter *iter;
@@ -4033,7 +4068,7 @@ ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
if (!cpumask_test_cpu(cpu, buffer->cpumask))
return NULL;
- iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ iter = kmalloc(sizeof(*iter), flags);
if (!iter)
return NULL;
@@ -4875,9 +4910,9 @@ static __init int test_ringbuffer(void)
rb_data[cpu].cnt = cpu;
rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
"rbtester/%d", cpu);
- if (WARN_ON(!rb_threads[cpu])) {
+ if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
pr_cont("FAILED\n");
- ret = -1;
+ ret = PTR_ERR(rb_threads[cpu]);
goto out_free;
}
@@ -4887,9 +4922,9 @@ static __init int test_ringbuffer(void)
/* Now create the rb hammer! */
rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
- if (WARN_ON(!rb_hammer)) {
+ if (WARN_ON(IS_ERR(rb_hammer))) {
pr_cont("FAILED\n");
- ret = -1;
+ ret = PTR_ERR(rb_hammer);
goto out_free;
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 059233abcfcf..5814e7386109 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -890,6 +890,7 @@ static struct {
{ trace_clock, "perf", 1 },
{ ktime_get_mono_fast_ns, "mono", 1 },
{ ktime_get_raw_fast_ns, "mono_raw", 1 },
+ { ktime_get_boot_fast_ns, "boot", 1 },
ARCH_TRACE_CLOCKS
};
@@ -1088,6 +1089,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
buf = tr->trace_buffer.buffer;
tr->trace_buffer.buffer = tr->max_buffer.buffer;
tr->max_buffer.buffer = buf;
@@ -1356,6 +1363,7 @@ static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
struct saved_cmdlines_buffer {
unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
unsigned *map_cmdline_to_pid;
+ unsigned *map_cmdline_to_tgid;
unsigned cmdline_num;
int cmdline_idx;
char *saved_cmdlines;
@@ -1389,12 +1397,23 @@ static int allocate_cmdlines_buffer(unsigned int val,
return -ENOMEM;
}
+ s->map_cmdline_to_tgid = kmalloc_array(val,
+ sizeof(*s->map_cmdline_to_tgid),
+ GFP_KERNEL);
+ if (!s->map_cmdline_to_tgid) {
+ kfree(s->map_cmdline_to_pid);
+ kfree(s->saved_cmdlines);
+ return -ENOMEM;
+ }
+
s->cmdline_idx = 0;
s->cmdline_num = val;
memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
sizeof(s->map_pid_to_cmdline));
memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
val * sizeof(*s->map_cmdline_to_pid));
+ memset(s->map_cmdline_to_tgid, NO_CMDLINE_MAP,
+ val * sizeof(*s->map_cmdline_to_tgid));
return 0;
}
@@ -1560,14 +1579,17 @@ static int trace_save_cmdline(struct task_struct *tsk)
if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
return 0;
+ preempt_disable();
/*
* It's not the end of the world if we don't get
* the lock, but we also don't want to spin
* nor do we want to disable interrupts,
* so if we miss here, then better luck next time.
*/
- if (!arch_spin_trylock(&trace_cmdline_lock))
+ if (!arch_spin_trylock(&trace_cmdline_lock)) {
+ preempt_enable();
return 0;
+ }
idx = savedcmd->map_pid_to_cmdline[tsk->pid];
if (idx == NO_CMDLINE_MAP) {
@@ -1590,8 +1612,9 @@ static int trace_save_cmdline(struct task_struct *tsk)
}
set_cmdline(idx, tsk->comm);
-
+ savedcmd->map_cmdline_to_tgid[idx] = tsk->tgid;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
return 1;
}
@@ -1633,6 +1656,35 @@ void trace_find_cmdline(int pid, char comm[])
preempt_enable();
}
+static int __find_tgid_locked(int pid)
+{
+ unsigned map;
+ int tgid;
+
+ map = savedcmd->map_pid_to_cmdline[pid];
+ if (map != NO_CMDLINE_MAP)
+ tgid = savedcmd->map_cmdline_to_tgid[map];
+ else
+ tgid = -1;
+
+ return tgid;
+}
+
+int trace_find_tgid(int pid)
+{
+ int tgid;
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+
+ tgid = __find_tgid_locked(pid);
+
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ return tgid;
+}
+
void tracing_record_cmdline(struct task_struct *tsk)
{
if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on())
@@ -1660,7 +1712,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
TRACE_FLAG_IRQS_NOSUPPORT |
#endif
((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
- ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
+ ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) |
(tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
(test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0);
}
@@ -1751,7 +1803,17 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
{
__buffer_unlock_commit(buffer, event);
- ftrace_trace_stack(tr, buffer, flags, 0, pc, regs);
+ /*
+ * If regs is not set, then skip the following callers:
+ * trace_buffer_unlock_commit_regs
+ * event_trigger_unlock_commit
+ * trace_event_buffer_commit
+ * trace_event_raw_event_sched_switch
+ * Note, we can still get here via blktrace, wakeup tracer
+ * and mmiotrace, but that's ok if they lose a function or
+ * two. They are that meaningful.
+ */
+ ftrace_trace_stack(tr, buffer, flags, regs ? 0 : 4, pc, regs);
ftrace_trace_userstack(buffer, flags, pc);
}
EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
@@ -1810,6 +1872,13 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
trace.skip = skip;
/*
+ * Add two, for this function and the call to save_stack_trace()
+ * If regs is set, then these functions will not be in the way.
+ */
+ if (!regs)
+ trace.skip += 2;
+
+ /*
* Since events can happen in NMIs there's no safe way to
* use the per cpu ftrace_stacks. We reserve it and if an interrupt
* or NMI comes in, it will just have to use the default
@@ -2180,6 +2249,7 @@ out:
}
EXPORT_SYMBOL_GPL(trace_vbprintk);
+__printf(3, 0)
static int
__trace_array_vprintk(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, va_list args)
@@ -2230,12 +2300,14 @@ __trace_array_vprintk(struct ring_buffer *buffer,
return len;
}
+__printf(3, 0)
int trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args)
{
return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
}
+__printf(3, 0)
int trace_array_printk(struct trace_array *tr,
unsigned long ip, const char *fmt, ...)
{
@@ -2251,6 +2323,7 @@ int trace_array_printk(struct trace_array *tr,
return ret;
}
+__printf(3, 4)
int trace_array_printk_buf(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, ...)
{
@@ -2266,6 +2339,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer,
return ret;
}
+__printf(2, 0)
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -2583,6 +2657,13 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m)
"# | | | | |\n");
}
+static void print_func_help_header_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+ print_event_info(buf, m);
+ seq_puts(m, "# TASK-PID TGID CPU# TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | | |\n");
+}
+
static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
{
print_event_info(buf, m);
@@ -2595,6 +2676,18 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
"# | | | |||| | |\n");
}
+static void print_func_help_header_irq_tgid(struct trace_buffer *buf, struct seq_file *m)
+{
+ print_event_info(buf, m);
+ seq_puts(m, "# _-----=> irqs-off\n");
+ seq_puts(m, "# / _----=> need-resched\n");
+ seq_puts(m, "# | / _---=> hardirq/softirq\n");
+ seq_puts(m, "# || / _--=> preempt-depth\n");
+ seq_puts(m, "# ||| / delay\n");
+ seq_puts(m, "# TASK-PID TGID CPU# |||| TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | | |||| | |\n");
+}
+
void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
{
@@ -2668,13 +2761,14 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
return;
- if (iter->started && cpumask_test_cpu(iter->cpu, iter->started))
+ if (cpumask_available(iter->started) &&
+ cpumask_test_cpu(iter->cpu, iter->started))
return;
if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries)
return;
- if (iter->started)
+ if (cpumask_available(iter->started))
cpumask_set_cpu(iter->cpu, iter->started);
/* Don't print started cpu buffer for the first entry of the trace */
@@ -2907,9 +3001,15 @@ void trace_default_header(struct seq_file *m)
} else {
if (!(trace_flags & TRACE_ITER_VERBOSE)) {
if (trace_flags & TRACE_ITER_IRQ_INFO)
- print_func_help_header_irq(iter->trace_buffer, m);
+ if (trace_flags & TRACE_ITER_TGID)
+ print_func_help_header_irq_tgid(iter->trace_buffer, m);
+ else
+ print_func_help_header_irq(iter->trace_buffer, m);
else
- print_func_help_header(iter->trace_buffer, m);
+ if (trace_flags & TRACE_ITER_TGID)
+ print_func_help_header_tgid(iter->trace_buffer, m);
+ else
+ print_func_help_header(iter->trace_buffer, m);
}
}
}
@@ -3094,7 +3194,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
+ ring_buffer_read_prepare(iter->trace_buffer->buffer,
+ cpu, GFP_KERNEL);
}
ring_buffer_read_prepare_sync();
for_each_tracing_cpu(cpu) {
@@ -3104,7 +3205,8 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
} else {
cpu = iter->cpu_file;
iter->buffer_iter[cpu] =
- ring_buffer_read_prepare(iter->trace_buffer->buffer, cpu);
+ ring_buffer_read_prepare(iter->trace_buffer->buffer,
+ cpu, GFP_KERNEL);
ring_buffer_read_prepare_sync();
ring_buffer_read_start(iter->buffer_iter[cpu]);
tracing_iter_reset(iter, cpu);
@@ -3226,11 +3328,17 @@ static int tracing_open(struct inode *inode, struct file *file)
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
int cpu = tracing_get_cpu(inode);
+ struct trace_buffer *trace_buf = &tr->trace_buffer;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (tr->current_trace->print_max)
+ trace_buf = &tr->max_buffer;
+#endif
if (cpu == RING_BUFFER_ALL_CPUS)
- tracing_reset_online_cpus(&tr->trace_buffer);
+ tracing_reset_online_cpus(trace_buf);
else
- tracing_reset(&tr->trace_buffer, cpu);
+ tracing_reset(trace_buf, cpu);
}
if (file->f_mode & FMODE_READ) {
@@ -3378,37 +3486,30 @@ static const struct file_operations show_traces_fops = {
.llseek = seq_lseek,
};
-/*
- * The tracer itself will not take this lock, but still we want
- * to provide a consistent cpumask to user-space:
- */
-static DEFINE_MUTEX(tracing_cpumask_update_lock);
-
-/*
- * Temporary storage for the character representation of the
- * CPU bitmask (and one more byte for the newline):
- */
-static char mask_str[NR_CPUS + 1];
-
static ssize_t
tracing_cpumask_read(struct file *filp, char __user *ubuf,
size_t count, loff_t *ppos)
{
struct trace_array *tr = file_inode(filp)->i_private;
+ char *mask_str;
int len;
- mutex_lock(&tracing_cpumask_update_lock);
+ len = snprintf(NULL, 0, "%*pb\n",
+ cpumask_pr_args(tr->tracing_cpumask)) + 1;
+ mask_str = kmalloc(len, GFP_KERNEL);
+ if (!mask_str)
+ return -ENOMEM;
- len = snprintf(mask_str, count, "%*pb\n",
+ len = snprintf(mask_str, len, "%*pb\n",
cpumask_pr_args(tr->tracing_cpumask));
if (len >= count) {
count = -EINVAL;
goto out_err;
}
- count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1);
+ count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
out_err:
- mutex_unlock(&tracing_cpumask_update_lock);
+ kfree(mask_str);
return count;
}
@@ -3428,8 +3529,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
if (err)
goto err_unlock;
- mutex_lock(&tracing_cpumask_update_lock);
-
local_irq_disable();
arch_spin_lock(&tr->max_lock);
for_each_tracing_cpu(cpu) {
@@ -3452,8 +3551,6 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
local_irq_enable();
cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
-
- mutex_unlock(&tracing_cpumask_update_lock);
free_cpumask_var(tracing_cpumask_new);
return count;
@@ -3917,10 +4014,15 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
{
char buf[64];
int r;
+ unsigned int n;
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
- r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
+ n = savedcmd->cmdline_num;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ r = scnprintf(buf, sizeof(buf), "%u\n", n);
return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
@@ -3929,6 +4031,7 @@ static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
{
kfree(s->saved_cmdlines);
kfree(s->map_cmdline_to_pid);
+ kfree(s->map_cmdline_to_tgid);
kfree(s);
}
@@ -3945,10 +4048,12 @@ static int tracing_resize_saved_cmdlines(unsigned int val)
return -ENOMEM;
}
+ preempt_disable();
arch_spin_lock(&trace_cmdline_lock);
savedcmd_temp = savedcmd;
savedcmd = s;
arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
free_saved_cmdlines_buffer(savedcmd_temp);
return 0;
@@ -4161,6 +4266,78 @@ static void trace_insert_enum_map(struct module *mod,
}
static ssize_t
+tracing_saved_tgids_read(struct file *file, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ char *file_buf;
+ char *buf;
+ int len = 0;
+ int i;
+ int *pids;
+ int n = 0;
+
+ preempt_disable();
+ arch_spin_lock(&trace_cmdline_lock);
+
+ pids = kmalloc_array(savedcmd->cmdline_num, 2*sizeof(int), GFP_KERNEL);
+ if (!pids) {
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < savedcmd->cmdline_num; i++) {
+ int pid;
+
+ pid = savedcmd->map_cmdline_to_pid[i];
+ if (pid == -1 || pid == NO_CMDLINE_MAP)
+ continue;
+
+ pids[n] = pid;
+ pids[n+1] = __find_tgid_locked(pid);
+ n += 2;
+ }
+ arch_spin_unlock(&trace_cmdline_lock);
+ preempt_enable();
+
+ if (n == 0) {
+ kfree(pids);
+ return 0;
+ }
+
+ /* enough to hold max pair of pids + space, lr and nul */
+ len = n * 12;
+ file_buf = kmalloc(len, GFP_KERNEL);
+ if (!file_buf) {
+ kfree(pids);
+ return -ENOMEM;
+ }
+
+ buf = file_buf;
+ for (i = 0; i < n && len > 0; i += 2) {
+ int r;
+
+ r = snprintf(buf, len, "%d %d\n", pids[i], pids[i+1]);
+ buf += r;
+ len -= r;
+ }
+
+ len = simple_read_from_buffer(ubuf, cnt, ppos,
+ file_buf, buf - file_buf);
+
+ kfree(file_buf);
+ kfree(pids);
+
+ return len;
+}
+
+static const struct file_operations tracing_saved_tgids_fops = {
+ .open = tracing_open_generic,
+ .read = tracing_saved_tgids_read,
+ .llseek = generic_file_llseek,
+};
+
+static ssize_t
tracing_set_trace_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
@@ -4623,7 +4800,6 @@ out:
return ret;
fail:
- kfree(iter->trace);
kfree(iter);
__trace_array_put(tr);
mutex_unlock(&trace_types_lock);
@@ -4701,7 +4877,7 @@ static int tracing_wait_pipe(struct file *filp)
*
* iter->pos will be 0 if we haven't read anything.
*/
- if (!tracing_is_on() && iter->pos)
+ if (!tracer_tracing_is_on(iter->tr) && iter->pos)
break;
mutex_unlock(&iter->mutex);
@@ -5237,7 +5413,7 @@ static int tracing_set_clock(struct trace_array *tr, const char *clockstr)
tracing_reset_online_cpus(&tr->trace_buffer);
#ifdef CONFIG_TRACER_MAX_TRACE
- if (tr->flags & TRACE_ARRAY_FL_GLOBAL && tr->max_buffer.buffer)
+ if (tr->max_buffer.buffer)
ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func);
tracing_reset_online_cpus(&tr->max_buffer);
#endif
@@ -5759,7 +5935,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int entries, size, i;
+ int entries, i;
ssize_t ret = 0;
#ifdef CONFIG_TRACER_MAX_TRACE
@@ -5810,14 +5986,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}
- /*
- * zero out any left over data, this is going to
- * user land.
- */
- size = ring_buffer_page_len(ref->page);
- if (size < PAGE_SIZE)
- memset(ref->page + size, 0, PAGE_SIZE - size);
-
page = virt_to_page(ref->page);
spd.pages[i] = page;
@@ -6060,11 +6228,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash,
return ret;
out_reg:
- ret = register_ftrace_function_probe(glob, ops, count);
+ ret = alloc_snapshot(&global_trace);
+ if (ret < 0)
+ goto out;
- if (ret >= 0)
- alloc_snapshot(&global_trace);
+ ret = register_ftrace_function_probe(glob, ops, count);
+ out:
return ret < 0 ? ret : 0;
}
@@ -6496,7 +6666,9 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
if (buffer) {
mutex_lock(&trace_types_lock);
- if (val) {
+ if (!!val == tracer_tracing_is_on(tr)) {
+ val = 0; /* do nothing */
+ } else if (val) {
tracer_tracing_on(tr);
if (tr->current_trace->start)
tr->current_trace->start(tr);
@@ -6542,6 +6714,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
buf->data = alloc_percpu(struct trace_array_cpu);
if (!buf->data) {
ring_buffer_free(buf->buffer);
+ buf->buffer = NULL;
return -ENOMEM;
}
@@ -6565,7 +6738,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
allocate_snapshot ? size : 1);
if (WARN_ON(ret)) {
ring_buffer_free(tr->trace_buffer.buffer);
+ tr->trace_buffer.buffer = NULL;
free_percpu(tr->trace_buffer.data);
+ tr->trace_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
@@ -6735,6 +6910,7 @@ static int instance_rmdir(const char *name)
}
kfree(tr->topts);
+ free_cpumask_var(tr->tracing_cpumask);
kfree(tr->name);
kfree(tr);
@@ -6790,6 +6966,9 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
trace_create_file("trace_marker", 0220, d_tracer,
tr, &tracing_mark_fops);
+ trace_create_file("saved_tgids", 0444, d_tracer,
+ tr, &tracing_saved_tgids_fops);
+
trace_create_file("trace_clock", 0644, d_tracer, tr,
&trace_clock_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 919d9d07686f..e1265f95457f 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -656,6 +656,7 @@ static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
extern cycle_t ftrace_now(int cpu);
extern void trace_find_cmdline(int pid, char comm[]);
+extern int trace_find_tgid(int pid);
#ifdef CONFIG_DYNAMIC_FTRACE
extern unsigned long ftrace_update_tot_cnt;
@@ -970,7 +971,8 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
FUNCTION_FLAGS \
FGRAPH_FLAGS \
STACK_FLAGS \
- BRANCH_FLAGS
+ BRANCH_FLAGS \
+ C(TGID, "print-tgid"),
/*
* By defining C, we can make TRACE_FLAGS a list of bit names
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 996f0fd34312..ba5392807912 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2300,6 +2300,7 @@ void trace_event_enum_update(struct trace_enum_map **map, int len)
{
struct trace_event_call *call, *p;
const char *last_system = NULL;
+ bool first = false;
int last_i;
int i;
@@ -2307,15 +2308,28 @@ void trace_event_enum_update(struct trace_enum_map **map, int len)
list_for_each_entry_safe(call, p, &ftrace_events, list) {
/* events are usually grouped together with systems */
if (!last_system || call->class->system != last_system) {
+ first = true;
last_i = 0;
last_system = call->class->system;
}
+ /*
+ * Since calls are grouped by systems, the likelyhood that the
+ * next call in the iteration belongs to the same system as the
+ * previous call is high. As an optimization, we skip seaching
+ * for a map[] that matches the call's system if the last call
+ * was from the same system. That's what last_i is for. If the
+ * call has the same system as the previous call, then last_i
+ * will be the index of the first map[] that has a matching
+ * system.
+ */
for (i = last_i; i < len; i++) {
if (call->class->system == map[i]->system) {
/* Save the first system if need be */
- if (!last_i)
+ if (first) {
last_i = i;
+ first = false;
+ }
update_event_printk(call, map[i]);
}
}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 6816302542b2..1ab2db6c127b 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -322,6 +322,9 @@ static int regex_match_full(char *str, struct regex *r, int len)
static int regex_match_front(char *str, struct regex *r, int len)
{
+ if (len < r->len)
+ return 0;
+
if (strncmp(str, r->pattern, r->len) == 0)
return 1;
return 0;
@@ -1979,6 +1982,10 @@ static int create_filter(struct trace_event_call *call,
if (err && set_str)
append_filter_err(ps, filter);
}
+ if (err && !set_str) {
+ free_event_filter(filter);
+ filter = NULL;
+ }
create_filter_finish(ps);
*filterp = filter;
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 42a4009fd75a..8be66a2b0cac 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -469,9 +469,10 @@ clear_event_triggers(struct trace_array *tr)
struct trace_event_file *file;
list_for_each_entry(file, &tr->events, list) {
- struct event_trigger_data *data;
- list_for_each_entry_rcu(data, &file->triggers, list) {
+ struct event_trigger_data *data, *n;
+ list_for_each_entry_safe(data, n, &file->triggers, list) {
trace_event_trigger_enable_disable(file, 0);
+ list_del_rcu(&data->list);
if (data->ops->free)
data->ops->free(data->ops, data);
}
@@ -662,6 +663,8 @@ event_trigger_callback(struct event_command *cmd_ops,
goto out_free;
out_reg:
+ /* Up the trigger_data count to make sure reg doesn't free it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
/*
* The above returns on success the # of functions enabled,
@@ -669,11 +672,13 @@ event_trigger_callback(struct event_command *cmd_ops,
* Consider no functions a failure too.
*/
if (!ret) {
+ cmd_ops->unreg(glob, trigger_ops, trigger_data, file);
ret = -ENOENT;
- goto out_free;
- } else if (ret < 0)
- goto out_free;
- ret = 0;
+ } else if (ret > 0)
+ ret = 0;
+
+ /* Down the counter of trigger_data or free it if not used anymore */
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
@@ -722,8 +727,10 @@ static int set_trigger_filter(char *filter_str,
/* The filter is for the 'trigger' event, not the triggered event */
ret = create_event_filter(file->event_call, filter_str, false, &filter);
- if (ret)
- goto out;
+ /*
+ * If create_event_filter() fails, filter still needs to be freed.
+ * Which the calling code will do with data->filter.
+ */
assign:
tmp = rcu_access_pointer(data->filter);
@@ -1226,6 +1233,9 @@ event_enable_trigger_func(struct event_command *cmd_ops,
goto out;
}
+ /* Up the trigger_data count to make sure nothing frees it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
+
if (trigger) {
number = strsep(&trigger, ":");
@@ -1276,6 +1286,7 @@ event_enable_trigger_func(struct event_command *cmd_ops,
goto out_disable;
/* Just return zero, not the number of enabled functions */
ret = 0;
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
@@ -1286,7 +1297,7 @@ event_enable_trigger_func(struct event_command *cmd_ops,
out_free:
if (cmd_ops->set_filter)
cmd_ops->set_filter(NULL, trigger_data, NULL);
- kfree(trigger_data);
+ event_trigger_free(trigger_ops, trigger_data);
kfree(enable_data);
goto out;
}
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index a663cbb84107..55002f20950f 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -8,6 +8,7 @@
*/
#include <linux/uaccess.h>
#include <linux/ftrace.h>
+#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/fs.h>
@@ -64,6 +65,9 @@ struct fgraph_data {
#define TRACE_GRAPH_INDENT 2
+/* Flag options */
+#define TRACE_GRAPH_PRINT_FLAT 0x80
+
static unsigned int max_depth;
static struct tracer_opt trace_opts[] = {
@@ -87,6 +91,8 @@ static struct tracer_opt trace_opts[] = {
{ TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) },
/* Include time within nested functions */
{ TRACER_OPT(graph-time, TRACE_GRAPH_GRAPH_TIME) },
+ /* Use standard trace formatting rather than hierarchical */
+ { TRACER_OPT(funcgraph-flat, TRACE_GRAPH_PRINT_FLAT) },
{ } /* Empty entry */
};
@@ -768,6 +774,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
struct ftrace_graph_ret *graph_ret;
struct ftrace_graph_ent *call;
unsigned long long duration;
+ int cpu = iter->cpu;
int i;
graph_ret = &ret_entry->ret;
@@ -776,10 +783,13 @@ print_graph_entry_leaf(struct trace_iterator *iter,
if (data) {
struct fgraph_cpu_data *cpu_data;
- int cpu = iter->cpu;
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
+ /* If a graph tracer ignored set_graph_notrace */
+ if (call->depth < -1)
+ call->depth += FTRACE_NOTRACE_DEPTH;
+
/*
* Comments display at + 1 to depth. Since
* this is a leaf function, keep the comments
@@ -788,7 +798,8 @@ print_graph_entry_leaf(struct trace_iterator *iter,
cpu_data->depth = call->depth - 1;
/* No need to keep this function around for this depth */
- if (call->depth < FTRACE_RETFUNC_DEPTH)
+ if (call->depth < FTRACE_RETFUNC_DEPTH &&
+ !WARN_ON_ONCE(call->depth < 0))
cpu_data->enter_funcs[call->depth] = 0;
}
@@ -801,6 +812,9 @@ print_graph_entry_leaf(struct trace_iterator *iter,
trace_seq_printf(s, "%ps();\n", (void *)call->func);
+ print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
+ cpu, iter->ent->pid, flags);
+
return trace_handle_return(s);
}
@@ -818,11 +832,16 @@ print_graph_entry_nested(struct trace_iterator *iter,
struct fgraph_cpu_data *cpu_data;
int cpu = iter->cpu;
+ /* If a graph tracer ignored set_graph_notrace */
+ if (call->depth < -1)
+ call->depth += FTRACE_NOTRACE_DEPTH;
+
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
cpu_data->depth = call->depth;
/* Save this function pointer to see if the exit matches */
- if (call->depth < FTRACE_RETFUNC_DEPTH)
+ if (call->depth < FTRACE_RETFUNC_DEPTH &&
+ !WARN_ON_ONCE(call->depth < 0))
cpu_data->enter_funcs[call->depth] = call->func;
}
@@ -1052,7 +1071,8 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
*/
cpu_data->depth = trace->depth - 1;
- if (trace->depth < FTRACE_RETFUNC_DEPTH) {
+ if (trace->depth < FTRACE_RETFUNC_DEPTH &&
+ !WARN_ON_ONCE(trace->depth < 0)) {
if (cpu_data->enter_funcs[trace->depth] != trace->func)
func_match = 0;
cpu_data->enter_funcs[trace->depth] = 0;
@@ -1165,6 +1185,9 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
int cpu = iter->cpu;
int ret;
+ if (flags & TRACE_GRAPH_PRINT_FLAT)
+ return TRACE_TYPE_UNHANDLED;
+
if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
return TRACE_TYPE_HANDLED;
@@ -1222,13 +1245,6 @@ print_graph_function(struct trace_iterator *iter)
return print_graph_function_flags(iter, tracer_flags.val);
}
-static enum print_line_t
-print_graph_function_event(struct trace_iterator *iter, int flags,
- struct trace_event *event)
-{
- return print_graph_function(iter);
-}
-
static void print_lat_header(struct seq_file *s, u32 flags)
{
static const char spaces[] = " " /* 16 spaces */
@@ -1297,6 +1313,11 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags)
struct trace_iterator *iter = s->private;
struct trace_array *tr = iter->tr;
+ if (flags & TRACE_GRAPH_PRINT_FLAT) {
+ trace_default_header(s);
+ return;
+ }
+
if (!(tr->trace_flags & TRACE_ITER_CONTEXT_INFO))
return;
@@ -1378,19 +1399,6 @@ func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
return 0;
}
-static struct trace_event_functions graph_functions = {
- .trace = print_graph_function_event,
-};
-
-static struct trace_event graph_trace_entry_event = {
- .type = TRACE_GRAPH_ENT,
- .funcs = &graph_functions,
-};
-
-static struct trace_event graph_trace_ret_event = {
- .type = TRACE_GRAPH_RET,
- .funcs = &graph_functions
-};
static struct tracer graph_trace __tracer_data = {
.name = "function_graph",
@@ -1467,16 +1475,6 @@ static __init int init_graph_trace(void)
{
max_bytes_for_cpu = snprintf(NULL, 0, "%d", nr_cpu_ids - 1);
- if (!register_trace_event(&graph_trace_entry_event)) {
- pr_warning("Warning: could not register graph trace events\n");
- return 1;
- }
-
- if (!register_trace_event(&graph_trace_ret_event)) {
- pr_warning("Warning: could not register graph trace events\n");
- return 1;
- }
-
return register_tracer(&graph_trace);
}
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index be3222b7d72e..21b162c07e83 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -16,6 +16,10 @@
#include "trace.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/preemptirq.h>
+
+#if defined(CONFIG_IRQSOFF_TRACER) || defined(CONFIG_PREEMPT_TRACER)
static struct trace_array *irqsoff_trace __read_mostly;
static int tracer_enabled __read_mostly;
@@ -451,63 +455,43 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1)
#else /* !CONFIG_PROVE_LOCKING */
/*
- * Stubs:
- */
-
-void trace_softirqs_on(unsigned long ip)
-{
-}
-
-void trace_softirqs_off(unsigned long ip)
-{
-}
-
-inline void print_irqtrace_events(struct task_struct *curr)
-{
-}
-
-/*
* We are only interested in hardirq on/off events:
*/
-void trace_hardirqs_on(void)
+static inline void tracer_hardirqs_on(void)
{
if (!preempt_trace() && irq_trace())
stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
}
-EXPORT_SYMBOL(trace_hardirqs_on);
-void trace_hardirqs_off(void)
+static inline void tracer_hardirqs_off(void)
{
if (!preempt_trace() && irq_trace())
start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
}
-EXPORT_SYMBOL(trace_hardirqs_off);
-__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
+static inline void tracer_hardirqs_on_caller(unsigned long caller_addr)
{
if (!preempt_trace() && irq_trace())
stop_critical_timing(CALLER_ADDR0, caller_addr);
}
-EXPORT_SYMBOL(trace_hardirqs_on_caller);
-__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
+static inline void tracer_hardirqs_off_caller(unsigned long caller_addr)
{
if (!preempt_trace() && irq_trace())
start_critical_timing(CALLER_ADDR0, caller_addr);
}
-EXPORT_SYMBOL(trace_hardirqs_off_caller);
#endif /* CONFIG_PROVE_LOCKING */
#endif /* CONFIG_IRQSOFF_TRACER */
#ifdef CONFIG_PREEMPT_TRACER
-void trace_preempt_on(unsigned long a0, unsigned long a1)
+static inline void tracer_preempt_on(unsigned long a0, unsigned long a1)
{
if (preempt_trace() && !irq_trace())
stop_critical_timing(a0, a1);
}
-void trace_preempt_off(unsigned long a0, unsigned long a1)
+static inline void tracer_preempt_off(unsigned long a0, unsigned long a1)
{
if (preempt_trace() && !irq_trace())
start_critical_timing(a0, a1);
@@ -770,3 +754,100 @@ __init static int init_irqsoff_tracer(void)
return 0;
}
core_initcall(init_irqsoff_tracer);
+#endif /* IRQSOFF_TRACER || PREEMPTOFF_TRACER */
+
+#ifndef CONFIG_IRQSOFF_TRACER
+static inline void tracer_hardirqs_on(void) { }
+static inline void tracer_hardirqs_off(void) { }
+static inline void tracer_hardirqs_on_caller(unsigned long caller_addr) { }
+static inline void tracer_hardirqs_off_caller(unsigned long caller_addr) { }
+#endif
+
+#ifndef CONFIG_PREEMPT_TRACER
+static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { }
+static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { }
+#endif
+
+/* Per-cpu variable to prevent redundant calls when IRQs already off */
+static DEFINE_PER_CPU(int, tracing_irq_cpu);
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PROVE_LOCKING)
+void trace_hardirqs_on(void)
+{
+ if (!this_cpu_read(tracing_irq_cpu))
+ return;
+
+ trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+ tracer_hardirqs_on();
+
+ this_cpu_write(tracing_irq_cpu, 0);
+}
+EXPORT_SYMBOL(trace_hardirqs_on);
+
+void trace_hardirqs_off(void)
+{
+ if (this_cpu_read(tracing_irq_cpu))
+ return;
+
+ this_cpu_write(tracing_irq_cpu, 1);
+
+ trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+ tracer_hardirqs_off();
+}
+EXPORT_SYMBOL(trace_hardirqs_off);
+
+__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
+{
+ if (!this_cpu_read(tracing_irq_cpu))
+ return;
+
+ trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr);
+ tracer_hardirqs_on_caller(caller_addr);
+
+ this_cpu_write(tracing_irq_cpu, 0);
+}
+EXPORT_SYMBOL(trace_hardirqs_on_caller);
+
+__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
+{
+ if (this_cpu_read(tracing_irq_cpu))
+ return;
+
+ this_cpu_write(tracing_irq_cpu, 1);
+
+ trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
+ tracer_hardirqs_off_caller(caller_addr);
+}
+EXPORT_SYMBOL(trace_hardirqs_off_caller);
+
+/*
+ * Stubs:
+ */
+
+void trace_softirqs_on(unsigned long ip)
+{
+}
+
+void trace_softirqs_off(unsigned long ip)
+{
+}
+
+inline void print_irqtrace_events(struct task_struct *curr)
+{
+}
+#endif
+
+#if defined(CONFIG_PREEMPT_TRACER) || \
+ (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS))
+void trace_preempt_on(unsigned long a0, unsigned long a1)
+{
+ trace_preempt_enable_rcuidle(a0, a1);
+ tracer_preempt_on(a0, a1);
+}
+
+void trace_preempt_off(unsigned long a0, unsigned long a1)
+{
+ trace_preempt_disable_rcuidle(a0, a1);
+ tracer_preempt_off(a0, a1);
+}
+#endif
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index 57149bce6aad..896458285fdd 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -50,14 +50,16 @@ static void ftrace_dump_buf(int skip_lines, long cpu_file)
if (cpu_file == RING_BUFFER_ALL_CPUS) {
for_each_tracing_cpu(cpu) {
iter.buffer_iter[cpu] =
- ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu);
+ ring_buffer_read_prepare(iter.trace_buffer->buffer,
+ cpu, GFP_ATOMIC);
ring_buffer_read_start(iter.buffer_iter[cpu]);
tracing_iter_reset(&iter, cpu);
}
} else {
iter.cpu_file = cpu_file;
iter.buffer_iter[cpu_file] =
- ring_buffer_read_prepare(iter.trace_buffer->buffer, cpu_file);
+ ring_buffer_read_prepare(iter.trace_buffer->buffer,
+ cpu_file, GFP_ATOMIC);
ring_buffer_read_start(iter.buffer_iter[cpu_file]);
tracing_iter_reset(&iter, cpu_file);
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index c9956440d0e6..f0ee722be520 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -349,11 +349,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
static int
enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
{
+ struct event_file_link *link = NULL;
int ret = 0;
if (file) {
- struct event_file_link *link;
-
link = kmalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
ret = -ENOMEM;
@@ -373,6 +372,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
else
ret = enable_kprobe(&tk->rp.kp);
}
+
+ if (ret) {
+ if (file) {
+ /* Notice the if is true on not WARN() */
+ if (!WARN_ON_ONCE(!link))
+ list_del_rcu(&link->list);
+ kfree(link);
+ tk->tp.flags &= ~TP_FLAG_TRACE;
+ } else {
+ tk->tp.flags &= ~TP_FLAG_PROFILE;
+ }
+ }
out:
return ret;
}
@@ -599,7 +610,7 @@ static int create_trace_kprobe(int argc, char **argv)
bool is_return = false, is_delete = false;
char *symbol = NULL, *event = NULL, *group = NULL;
char *arg;
- unsigned long offset = 0;
+ long offset = 0;
void *addr = NULL;
char buf[MAX_EVENT_NAME_LEN];
@@ -659,30 +670,25 @@ static int create_trace_kprobe(int argc, char **argv)
pr_info("Probe point is not specified.\n");
return -EINVAL;
}
- if (isdigit(argv[1][0])) {
- if (is_return) {
- pr_info("Return probe point must be a symbol.\n");
- return -EINVAL;
- }
- /* an address specified */
- ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr);
- if (ret) {
- pr_info("Failed to parse address.\n");
- return ret;
- }
- } else {
+
+ /* try to parse an address. if that fails, try to read the
+ * input as a symbol. */
+ if (kstrtoul(argv[1], 0, (unsigned long *)&addr)) {
/* a symbol specified */
symbol = argv[1];
/* TODO: support .init module functions */
ret = traceprobe_split_symbol_offset(symbol, &offset);
- if (ret) {
- pr_info("Failed to parse symbol.\n");
+ if (ret || offset < 0 || offset > UINT_MAX) {
+ pr_info("Failed to parse either an address or a symbol.\n");
return ret;
}
if (offset && is_return) {
pr_info("Return probe must be used without offset.\n");
return -EINVAL;
}
+ } else if (is_return) {
+ pr_info("Return probe point must be a symbol.\n");
+ return -EINVAL;
}
argc -= 2; argv += 2;
@@ -1471,6 +1477,11 @@ static __init int kprobe_trace_self_tests_init(void)
end:
release_all_trace_kprobes();
+ /*
+ * Wait for the optimizer work to finish. Otherwise it might fiddle
+ * with probes in already freed __init text.
+ */
+ wait_for_kprobe_optimizer();
if (warn)
pr_cont("NG: Some tests are failed. Please check them.\n");
else
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 282982195e09..3bc4b6de0f4d 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -526,11 +526,21 @@ int trace_print_context(struct trace_iterator *iter)
unsigned long long t;
unsigned long secs, usec_rem;
char comm[TASK_COMM_LEN];
+ int tgid;
trace_find_cmdline(entry->pid, comm);
- trace_seq_printf(s, "%16s-%-5d [%03d] ",
- comm, entry->pid, iter->cpu);
+ trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+
+ if (tr->trace_flags & TRACE_ITER_TGID) {
+ tgid = trace_find_tgid(entry->pid);
+ if (tgid < 0)
+ trace_seq_puts(s, "(-----) ");
+ else
+ trace_seq_printf(s, "(%5d) ", tgid);
+ }
+
+ trace_seq_printf(s, "[%03d] ", iter->cpu);
if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
trace_print_lat_fmt(s, entry);
@@ -845,6 +855,174 @@ static struct trace_event trace_fn_event = {
.funcs = &trace_fn_funcs,
};
+/* TRACE_GRAPH_ENT */
+static enum print_line_t trace_graph_ent_trace(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct trace_seq *s = &iter->seq;
+ struct ftrace_graph_ent_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ trace_seq_puts(s, "graph_ent: func=");
+ if (trace_seq_has_overflowed(s))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (!seq_print_ip_sym(s, field->graph_ent.func, flags))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ trace_seq_puts(s, "\n");
+ if (trace_seq_has_overflowed(s))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ trace_seq_printf(&iter->seq, "%lx %d\n",
+ field->graph_ent.func,
+ field->graph_ent.depth);
+ if (trace_seq_has_overflowed(&iter->seq))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_HEX_FIELD(s, field->graph_ent.func);
+ SEQ_PUT_HEX_FIELD(s, field->graph_ent.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ent_bin(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ent_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD(s, field->graph_ent.func);
+ SEQ_PUT_FIELD(s, field->graph_ent.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event_functions trace_graph_ent_funcs = {
+ .trace = trace_graph_ent_trace,
+ .raw = trace_graph_ent_raw,
+ .hex = trace_graph_ent_hex,
+ .binary = trace_graph_ent_bin,
+};
+
+static struct trace_event trace_graph_ent_event = {
+ .type = TRACE_GRAPH_ENT,
+ .funcs = &trace_graph_ent_funcs,
+};
+
+/* TRACE_GRAPH_RET */
+static enum print_line_t trace_graph_ret_trace(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct trace_seq *s = &iter->seq;
+ struct trace_entry *entry = iter->ent;
+ struct ftrace_graph_ret_entry *field;
+
+ trace_assign_type(field, entry);
+
+ trace_seq_puts(s, "graph_ret: func=");
+ if (trace_seq_has_overflowed(s))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ if (!seq_print_ip_sym(s, field->ret.func, flags))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ trace_seq_puts(s, "\n");
+ if (trace_seq_has_overflowed(s))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+
+ trace_assign_type(field, iter->ent);
+
+ trace_seq_printf(&iter->seq, "%lx %lld %lld %ld %d\n",
+ field->ret.func,
+ field->ret.calltime,
+ field->ret.rettime,
+ field->ret.overrun,
+ field->ret.depth);
+ if (trace_seq_has_overflowed(&iter->seq))
+ return TRACE_TYPE_PARTIAL_LINE;
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_HEX_FIELD(s, field->ret.func);
+ SEQ_PUT_HEX_FIELD(s, field->ret.calltime);
+ SEQ_PUT_HEX_FIELD(s, field->ret.rettime);
+ SEQ_PUT_HEX_FIELD(s, field->ret.overrun);
+ SEQ_PUT_HEX_FIELD(s, field->ret.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t trace_graph_ret_bin(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
+{
+ struct ftrace_graph_ret_entry *field;
+ struct trace_seq *s = &iter->seq;
+
+ trace_assign_type(field, iter->ent);
+
+ SEQ_PUT_FIELD(s, field->ret.func);
+ SEQ_PUT_FIELD(s, field->ret.calltime);
+ SEQ_PUT_FIELD(s, field->ret.rettime);
+ SEQ_PUT_FIELD(s, field->ret.overrun);
+ SEQ_PUT_FIELD(s, field->ret.depth);
+
+ return TRACE_TYPE_HANDLED;
+}
+
+static struct trace_event_functions trace_graph_ret_funcs = {
+ .trace = trace_graph_ret_trace,
+ .raw = trace_graph_ret_raw,
+ .hex = trace_graph_ret_hex,
+ .binary = trace_graph_ret_bin,
+};
+
+static struct trace_event trace_graph_ret_event = {
+ .type = TRACE_GRAPH_RET,
+ .funcs = &trace_graph_ret_funcs,
+};
+
/* TRACE_CTX an TRACE_WAKE */
static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
char *delim)
@@ -1222,6 +1400,8 @@ static struct trace_event trace_print_event = {
static struct trace_event *events[] __initdata = {
&trace_fn_event,
+ &trace_graph_ent_event,
+ &trace_graph_ret_event,
&trace_ctx_event,
&trace_wake_event,
&trace_stack_event,
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 1769a81da8a7..741c00b90fdc 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -293,7 +293,7 @@ static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
}
/* Split symbol and offset. */
-int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
+int traceprobe_split_symbol_offset(char *symbol, long *offset)
{
char *tmp;
int ret;
@@ -301,13 +301,11 @@ int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset)
if (!offset)
return -EINVAL;
- tmp = strchr(symbol, '+');
+ tmp = strpbrk(symbol, "+-");
if (tmp) {
- /* skip sign because kstrtoul doesn't accept '+' */
- ret = kstrtoul(tmp + 1, 0, offset);
+ ret = kstrtol(tmp, 0, offset);
if (ret)
return ret;
-
*tmp = '\0';
} else
*offset = 0;
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index f6398db09114..0afe921df8c8 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -335,7 +335,7 @@ extern int traceprobe_conflict_field_name(const char *name,
extern void traceprobe_update_arg(struct probe_arg *arg);
extern void traceprobe_free_probe_arg(struct probe_arg *arg);
-extern int traceprobe_split_symbol_offset(char *symbol, unsigned long *offset);
+extern int traceprobe_split_symbol_offset(char *symbol, long *offset);
extern ssize_t traceprobe_probes_write(struct file *file,
const char __user *buffer, size_t count, loff_t *ppos,
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index b0f86ea77881..ca70d11b8aa7 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -272,7 +272,7 @@ static int trace_selftest_ops(struct trace_array *tr, int cnt)
goto out_free;
if (cnt > 1) {
if (trace_selftest_test_global_cnt == 0)
- goto out;
+ goto out_free;
}
if (trace_selftest_test_dyn_cnt == 0)
goto out_free;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index d2f6d0be3503..518e62a398d2 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -149,6 +149,15 @@ static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
return;
ret = strncpy_from_user(dst, src, maxlen);
+ if (ret == maxlen)
+ dst[ret - 1] = '\0';
+ else if (ret >= 0)
+ /*
+ * Include the terminating null byte. In this case it
+ * was copied by strncpy_from_user but not accounted
+ * for in ret.
+ */
+ ret++;
if (ret < 0) { /* Failed to fetch string */
((u8 *)get_rloc_data(dest))[0] = '\0';
@@ -967,7 +976,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
list_del_rcu(&link->list);
/* synchronize with u{,ret}probe_trace_func */
- synchronize_sched();
+ synchronize_rcu();
kfree(link);
if (!list_empty(&tu->tp.files))
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index ecd536de603a..eda85bbf1c2e 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -202,7 +202,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
lockdep_is_held(&tracepoints_mutex));
old = func_add(&tp_funcs, func, prio);
if (IS_ERR(old)) {
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
return PTR_ERR(old);
}
@@ -235,7 +235,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
lockdep_is_held(&tracepoints_mutex));
old = func_remove(&tp_funcs, func);
if (IS_ERR(old)) {
- WARN_ON_ONCE(1);
+ WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
return PTR_ERR(old);
}
diff --git a/kernel/uid16.c b/kernel/uid16.c
index d58cc4d8f0d1..651aaa5221ec 100644
--- a/kernel/uid16.c
+++ b/kernel/uid16.c
@@ -190,6 +190,7 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist)
return retval;
}
+ groups_sort(group_info);
retval = set_current_groups(group_info);
put_group_info(group_info);
diff --git a/kernel/user.c b/kernel/user.c
index b069ccbfb0b0..41e94e453836 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -16,6 +16,7 @@
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
+#include <linux/proc_fs.h>
#include <linux/proc_ns.h>
/*
@@ -201,6 +202,7 @@ struct user_struct *alloc_uid(kuid_t uid)
}
spin_unlock_irq(&uidhash_lock);
}
+ proc_register_uid(uid);
return up;
@@ -222,6 +224,7 @@ static int __init uid_cache_init(void)
spin_lock_irq(&uidhash_lock);
uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
spin_unlock_irq(&uidhash_lock);
+ proc_register_uid(GLOBAL_ROOT_UID);
return 0;
}
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 88fefa68c516..a965df4b54f5 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -602,9 +602,26 @@ static ssize_t map_write(struct file *file, const char __user *buf,
struct uid_gid_map new_map;
unsigned idx;
struct uid_gid_extent *extent = NULL;
- unsigned long page = 0;
+ unsigned long page;
char *kbuf, *pos, *next_line;
- ssize_t ret = -EINVAL;
+ ssize_t ret;
+
+ /* Only allow < page size writes at the beginning of the file */
+ if ((*ppos != 0) || (count >= PAGE_SIZE))
+ return -EINVAL;
+
+ /* Get a buffer */
+ page = __get_free_page(GFP_TEMPORARY);
+ kbuf = (char *) page;
+ if (!page)
+ return -ENOMEM;
+
+ /* Slurp in the user data */
+ if (copy_from_user(kbuf, buf, count)) {
+ free_page(page);
+ return -EFAULT;
+ }
+ kbuf[count] = '\0';
/*
* The userns_state_mutex serializes all writes to any given map.
@@ -638,24 +655,6 @@ static ssize_t map_write(struct file *file, const char __user *buf,
if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
goto out;
- /* Get a buffer */
- ret = -ENOMEM;
- page = __get_free_page(GFP_TEMPORARY);
- kbuf = (char *) page;
- if (!page)
- goto out;
-
- /* Only allow < page size writes at the beginning of the file */
- ret = -EINVAL;
- if ((*ppos != 0) || (count >= PAGE_SIZE))
- goto out;
-
- /* Slurp in the user data */
- ret = -EFAULT;
- if (copy_from_user(kbuf, buf, count))
- goto out;
- kbuf[count] = '\0';
-
/* Parse the user data */
ret = -EINVAL;
pos = kbuf;
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index c8eac43267e9..d2b3b2973456 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -17,7 +17,7 @@
#ifdef CONFIG_PROC_SYSCTL
-static void *get_uts(struct ctl_table *table, int write)
+static void *get_uts(struct ctl_table *table)
{
char *which = table->data;
struct uts_namespace *uts_ns;
@@ -25,21 +25,9 @@ static void *get_uts(struct ctl_table *table, int write)
uts_ns = current->nsproxy->uts_ns;
which = (which - (char *)&init_uts_ns) + (char *)uts_ns;
- if (!write)
- down_read(&uts_sem);
- else
- down_write(&uts_sem);
return which;
}
-static void put_uts(struct ctl_table *table, int write, void *which)
-{
- if (!write)
- up_read(&uts_sem);
- else
- up_write(&uts_sem);
-}
-
/*
* Special case of dostring for the UTS structure. This has locks
* to observe. Should this be in kernel/sys.c ????
@@ -49,13 +37,34 @@ static int proc_do_uts_string(struct ctl_table *table, int write,
{
struct ctl_table uts_table;
int r;
+ char tmp_data[__NEW_UTS_LEN + 1];
+
memcpy(&uts_table, table, sizeof(uts_table));
- uts_table.data = get_uts(table, write);
+ uts_table.data = tmp_data;
+
+ /*
+ * Buffer the value in tmp_data so that proc_dostring() can be called
+ * without holding any locks.
+ * We also need to read the original value in the write==1 case to
+ * support partial writes.
+ */
+ down_read(&uts_sem);
+ memcpy(tmp_data, get_uts(table), sizeof(tmp_data));
+ up_read(&uts_sem);
r = proc_dostring(&uts_table, write, buffer, lenp, ppos);
- put_uts(table, write, uts_table.data);
- if (write)
+ if (write) {
+ /*
+ * Write back the new value.
+ * Note that, since we dropped uts_sem, the result can
+ * theoretically be incorrect if there are two parallel writes
+ * at non-zero offsets to the same sysctl.
+ */
+ down_write(&uts_sem);
+ memcpy(get_uts(table), tmp_data, sizeof(tmp_data));
+ up_write(&uts_sem);
proc_sys_poll_notify(table->poll);
+ }
return r;
}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 198137b1cadc..b718530034d2 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -103,6 +103,11 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
+#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static cpumask_t __read_mostly watchdog_cpus;
+#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif
static unsigned long soft_lockup_nmi_warn;
@@ -114,7 +119,7 @@ static unsigned long soft_lockup_nmi_warn;
#ifdef CONFIG_HARDLOCKUP_DETECTOR
unsigned int __read_mostly hardlockup_panic =
CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE;
-static unsigned long hardlockup_allcpu_dumped;
+static unsigned long __maybe_unused hardlockup_allcpu_dumped;
/*
* We may not want to enable hard lockup detection by default in all cases,
* for example when running the kernel as a guest on a hypervisor. In these
@@ -271,7 +276,7 @@ void touch_softlockup_watchdog_sync(void)
__this_cpu_write(watchdog_touch_ts, 0);
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
/* watchdog detector functions */
static bool is_hardlockup(void)
{
@@ -285,6 +290,76 @@ static bool is_hardlockup(void)
}
#endif
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static unsigned int watchdog_next_cpu(unsigned int cpu)
+{
+ cpumask_t cpus = watchdog_cpus;
+ unsigned int next_cpu;
+
+ next_cpu = cpumask_next(cpu, &cpus);
+ if (next_cpu >= nr_cpu_ids)
+ next_cpu = cpumask_first(&cpus);
+
+ if (next_cpu == cpu)
+ return nr_cpu_ids;
+
+ return next_cpu;
+}
+
+static int is_hardlockup_other_cpu(unsigned int cpu)
+{
+ unsigned long hrint = per_cpu(hrtimer_interrupts, cpu);
+
+ if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint)
+ return 1;
+
+ per_cpu(hrtimer_interrupts_saved, cpu) = hrint;
+ return 0;
+}
+
+static void watchdog_check_hardlockup_other_cpu(void)
+{
+ unsigned int next_cpu;
+
+ /*
+ * Test for hardlockups every 3 samples. The sample period is
+ * watchdog_thresh * 2 / 5, so 3 samples gets us back to slightly over
+ * watchdog_thresh (over by 20%).
+ */
+ if (__this_cpu_read(hrtimer_interrupts) % 3 != 0)
+ return;
+
+ /* check for a hardlockup on the next cpu */
+ next_cpu = watchdog_next_cpu(smp_processor_id());
+ if (next_cpu >= nr_cpu_ids)
+ return;
+
+ smp_rmb();
+
+ if (per_cpu(watchdog_nmi_touch, next_cpu) == true) {
+ per_cpu(watchdog_nmi_touch, next_cpu) = false;
+ return;
+ }
+
+ if (is_hardlockup_other_cpu(next_cpu)) {
+ /* only warn once */
+ if (per_cpu(hard_watchdog_warn, next_cpu) == true)
+ return;
+
+ if (hardlockup_panic)
+ panic("Watchdog detected hard LOCKUP on cpu %u", next_cpu);
+ else
+ WARN(1, "Watchdog detected hard LOCKUP on cpu %u", next_cpu);
+
+ per_cpu(hard_watchdog_warn, next_cpu) = true;
+ } else {
+ per_cpu(hard_watchdog_warn, next_cpu) = false;
+ }
+}
+#else
+static inline void watchdog_check_hardlockup_other_cpu(void) { return; }
+#endif
+
static int is_softlockup(unsigned long touch_ts)
{
unsigned long now = get_timestamp();
@@ -297,7 +372,7 @@ static int is_softlockup(unsigned long touch_ts)
return 0;
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
static struct perf_event_attr wd_hw_attr = {
.type = PERF_TYPE_HARDWARE,
@@ -328,7 +403,6 @@ static void watchdog_overflow_callback(struct perf_event *event,
*/
if (is_hardlockup()) {
int this_cpu = smp_processor_id();
- struct pt_regs *regs = get_irq_regs();
/* only print hardlockups once */
if (__this_cpu_read(hard_watchdog_warn) == true)
@@ -360,7 +434,7 @@ static void watchdog_overflow_callback(struct perf_event *event,
__this_cpu_write(hard_watchdog_warn, false);
return;
}
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */
static void watchdog_interrupt_count(void)
{
@@ -384,6 +458,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
/* kick the hardlockup detector */
watchdog_interrupt_count();
+ /* test for hardlockups on the next cpu */
+ watchdog_check_hardlockup_other_cpu();
+
/* kick the softlockup detector */
wake_up_process(__this_cpu_read(softlockup_watchdog));
@@ -561,7 +638,7 @@ static void watchdog(unsigned int cpu)
watchdog_nmi_disable(cpu);
}
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_NMI
/*
* People like the simple clean cpu node info on boot.
* Reduce the watchdog noise by only printing messages
@@ -660,9 +737,44 @@ static void watchdog_nmi_disable(unsigned int cpu)
}
#else
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU
+static int watchdog_nmi_enable(unsigned int cpu)
+{
+ /*
+ * The new cpu will be marked online before the first hrtimer interrupt
+ * runs on it. If another cpu tests for a hardlockup on the new cpu
+ * before it has run its first hrtimer, it will get a false positive.
+ * Touch the watchdog on the new cpu to delay the first check for at
+ * least 3 sampling periods to guarantee one hrtimer has run on the new
+ * cpu.
+ */
+ per_cpu(watchdog_nmi_touch, cpu) = true;
+ smp_wmb();
+ cpumask_set_cpu(cpu, &watchdog_cpus);
+ return 0;
+}
+
+static void watchdog_nmi_disable(unsigned int cpu)
+{
+ unsigned int next_cpu = watchdog_next_cpu(cpu);
+
+ /*
+ * Offlining this cpu will cause the cpu before this one to start
+ * checking the one after this one. If this cpu just finished checking
+ * the next cpu and updating hrtimer_interrupts_saved, and then the
+ * previous cpu checks it within one sample period, it will trigger a
+ * false positive. Touch the watchdog on the next cpu to prevent it.
+ */
+ if (next_cpu < nr_cpu_ids)
+ per_cpu(watchdog_nmi_touch, next_cpu) = true;
+ smp_wmb();
+ cpumask_clear_cpu(cpu, &watchdog_cpus);
+}
+#else
static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
static void watchdog_nmi_disable(unsigned int cpu) { return; }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_OTHER_CPU */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_NMI */
static struct smp_hotplug_thread watchdog_threads = {
.store = &softlockup_watchdog,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 2c2f971f3e75..d8a2084b88db 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -68,6 +68,7 @@ enum {
* attach_mutex to avoid changing binding state while
* worker_attach_to_pool() is in progress.
*/
+ POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */
POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */
/* worker flags */
@@ -163,7 +164,6 @@ struct worker_pool {
/* L: hash of busy workers */
/* see manage_workers() for details on the two manager mutexes */
- struct mutex manager_arb; /* manager arbitration */
struct worker *manager; /* L: purely informational */
struct mutex attach_mutex; /* attach/detach exclusion */
struct list_head workers; /* A: attached workers */
@@ -295,6 +295,7 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf;
static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */
static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */
+static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */
static LIST_HEAD(workqueues); /* PR: list of all workqueues */
static bool workqueue_freezing; /* PL: have wqs started freezing? */
@@ -808,7 +809,7 @@ static bool need_to_create_worker(struct worker_pool *pool)
/* Do we have too many workers and should some go away? */
static bool too_many_workers(struct worker_pool *pool)
{
- bool managing = mutex_is_locked(&pool->manager_arb);
+ bool managing = pool->flags & POOL_MANAGER_ACTIVE;
int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
int nr_busy = pool->nr_workers - nr_idle;
@@ -1478,6 +1479,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
struct timer_list *timer = &dwork->timer;
struct work_struct *work = &dwork->work;
+ WARN_ON_ONCE(!wq);
WARN_ON_ONCE(timer->function != delayed_work_timer_fn ||
timer->data != (unsigned long)dwork);
WARN_ON_ONCE(timer_pending(timer));
@@ -1952,24 +1954,17 @@ static bool manage_workers(struct worker *worker)
{
struct worker_pool *pool = worker->pool;
- /*
- * Anyone who successfully grabs manager_arb wins the arbitration
- * and becomes the manager. mutex_trylock() on pool->manager_arb
- * failure while holding pool->lock reliably indicates that someone
- * else is managing the pool and the worker which failed trylock
- * can proceed to executing work items. This means that anyone
- * grabbing manager_arb is responsible for actually performing
- * manager duties. If manager_arb is grabbed and released without
- * actual management, the pool may stall indefinitely.
- */
- if (!mutex_trylock(&pool->manager_arb))
+ if (pool->flags & POOL_MANAGER_ACTIVE)
return false;
+
+ pool->flags |= POOL_MANAGER_ACTIVE;
pool->manager = worker;
maybe_create_worker(pool);
pool->manager = NULL;
- mutex_unlock(&pool->manager_arb);
+ pool->flags &= ~POOL_MANAGER_ACTIVE;
+ wake_up(&wq_manager_wait);
return true;
}
@@ -3119,7 +3114,6 @@ static int init_worker_pool(struct worker_pool *pool)
setup_timer(&pool->mayday_timer, pool_mayday_timeout,
(unsigned long)pool);
- mutex_init(&pool->manager_arb);
mutex_init(&pool->attach_mutex);
INIT_LIST_HEAD(&pool->workers);
@@ -3189,13 +3183,15 @@ static void put_unbound_pool(struct worker_pool *pool)
hash_del(&pool->hash_node);
/*
- * Become the manager and destroy all workers. Grabbing
- * manager_arb prevents @pool's workers from blocking on
- * attach_mutex.
+ * Become the manager and destroy all workers. This prevents
+ * @pool's workers from blocking on attach_mutex. We're the last
+ * manager and @pool gets freed with the flag set.
*/
- mutex_lock(&pool->manager_arb);
-
spin_lock_irq(&pool->lock);
+ wait_event_lock_irq(wq_manager_wait,
+ !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock);
+ pool->flags |= POOL_MANAGER_ACTIVE;
+
while ((worker = first_idle_worker(pool)))
destroy_worker(worker);
WARN_ON(pool->nr_workers || pool->nr_idle);
@@ -3209,8 +3205,6 @@ static void put_unbound_pool(struct worker_pool *pool)
if (pool->detach_completion)
wait_for_completion(pool->detach_completion);
- mutex_unlock(&pool->manager_arb);
-
/* shut down the timers */
del_timer_sync(&pool->idle_timer);
del_timer_sync(&pool->mayday_timer);
@@ -3647,8 +3641,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
return -EINVAL;
/* creating multiple pwqs breaks ordering guarantee */
- if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
- return -EINVAL;
+ if (!list_empty(&wq->pwqs)) {
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+ return -EINVAL;
+
+ wq->flags &= ~__WQ_ORDERED;
+ }
ctx = apply_wqattrs_prepare(wq, attrs);
@@ -3834,6 +3832,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
struct workqueue_struct *wq;
struct pool_workqueue *pwq;
+ /*
+ * Unbound && max_active == 1 used to imply ordered, which is no
+ * longer the case on NUMA machines due to per-node pools. While
+ * alloc_ordered_workqueue() is the right way to create an ordered
+ * workqueue, keep the previous behavior to avoid subtle breakages
+ * on NUMA.
+ */
+ if ((flags & WQ_UNBOUND) && max_active == 1)
+ flags |= __WQ_ORDERED;
+
/* see the comment above the definition of WQ_POWER_EFFICIENT */
if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
flags |= WQ_UNBOUND;
@@ -4022,13 +4030,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
struct pool_workqueue *pwq;
/* disallow meddling with max_active for ordered workqueues */
- if (WARN_ON(wq->flags & __WQ_ORDERED))
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return;
max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
mutex_lock(&wq->mutex);
+ wq->flags &= ~__WQ_ORDERED;
wq->saved_max_active = max_active;
for_each_pwq(pwq, wq)
@@ -4039,6 +4048,22 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
EXPORT_SYMBOL_GPL(workqueue_set_max_active);
/**
+ * current_work - retrieve %current task's work struct
+ *
+ * Determine if %current task is a workqueue worker and what it's working on.
+ * Useful to find out the context that the %current task is running in.
+ *
+ * Return: work struct if %current task is a workqueue worker, %NULL otherwise.
+ */
+struct work_struct *current_work(void)
+{
+ struct worker *worker = current_wq_worker();
+
+ return worker ? worker->current_work : NULL;
+}
+EXPORT_SYMBOL(current_work);
+
+/**
* current_is_workqueue_rescuer - is %current workqueue rescuer?
*
* Determine whether %current is a workqueue rescuer. Can be used from
@@ -5154,7 +5179,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
* attributes breaks ordering guarantee. Disallow exposing ordered
* workqueues.
*/
- if (WARN_ON(wq->flags & __WQ_ORDERED))
+ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
return -EINVAL;
wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);
@@ -5174,7 +5199,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
ret = device_register(&wq_dev->dev);
if (ret) {
- kfree(wq_dev);
+ put_device(&wq_dev->dev);
wq->wq_dev = NULL;
return ret;
}
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 45215870ac6c..3fa9c146fccb 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -9,6 +9,7 @@
#include <linux/workqueue.h>
#include <linux/kthread.h>
+#include <linux/preempt.h>
struct worker_pool;
@@ -59,7 +60,7 @@ struct worker {
*/
static inline struct worker *current_wq_worker(void)
{
- if (current->flags & PF_WQ_WORKER)
+ if (in_task() && (current->flags & PF_WQ_WORKER))
return kthread_data(current);
return NULL;
}