Merge branch 'timers/posixtimers' into timers/tracing

Merge reason: timer tracepoint patches depend on both branches

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

4 files changed, 175 insertions, 157 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 021e1138556e..14cf79f14237 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -62,6 +62,7 @@
 #include <linux/fs_struct.h>
 #include <linux/magic.h>
 #include <linux/perf_counter.h>
+#include <linux/posix-timers.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -790,10 +791,10 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
         thread_group_cputime_init(sig);
 
         /* Expiration times and increments. */
-        sig->it_virt_expires = cputime_zero;
-        sig->it_virt_incr = cputime_zero;
-        sig->it_prof_expires = cputime_zero;
-        sig->it_prof_incr = cputime_zero;
+        sig->it[CPUCLOCK_PROF].expires = cputime_zero;
+        sig->it[CPUCLOCK_PROF].incr = cputime_zero;
+        sig->it[CPUCLOCK_VIRT].expires = cputime_zero;
+        sig->it[CPUCLOCK_VIRT].incr = cputime_zero;
 
         /* Cached expiration times. */
         sig->cputime_expires.prof_exp = cputime_zero;
diff --git a/kernel/itimer.c b/kernel/itimer.c
index 58762f7077ec..8078a32d3b10 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -41,10 +41,43 @@ static struct timeval itimer_get_remtime(struct hrtimer *timer)
         return ktime_to_timeval(rem);
 }
 
+static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+                           struct itimerval *const value)
+{
+        cputime_t cval, cinterval;
+        struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+        spin_lock_irq(&tsk->sighand->siglock);
+
+        cval = it->expires;
+        cinterval = it->incr;
+        if (!cputime_eq(cval, cputime_zero)) {
+                struct task_cputime cputime;
+                cputime_t t;
+
+                thread_group_cputimer(tsk, &cputime);
+                if (clock_id == CPUCLOCK_PROF)
+                        t = cputime_add(cputime.utime, cputime.stime);
+                else
+                        /* CPUCLOCK_VIRT */
+                        t = cputime.utime;
+
+                if (cputime_le(cval, t))
+                        /* about to fire */
+                        cval = cputime_one_jiffy;
+                else
+                        cval = cputime_sub(cval, t);
+        }
+
+        spin_unlock_irq(&tsk->sighand->siglock);
+
+        cputime_to_timeval(cval, &value->it_value);
+        cputime_to_timeval(cinterval, &value->it_interval);
+}
+
 int do_getitimer(int which, struct itimerval *value)
 {
         struct task_struct *tsk = current;
-        cputime_t cinterval, cval;
 
         switch (which) {
         case ITIMER_REAL:
@@ -55,44 +88,10 @@ int do_getitimer(int which, struct itimerval *value)
                 spin_unlock_irq(&tsk->sighand->siglock);
                 break;
         case ITIMER_VIRTUAL:
-                spin_lock_irq(&tsk->sighand->siglock);
-                cval = tsk->signal->it_virt_expires;
-                cinterval = tsk->signal->it_virt_incr;
-                if (!cputime_eq(cval, cputime_zero)) {
-                        struct task_cputime cputime;
-                        cputime_t utime;
-
-                        thread_group_cputimer(tsk, &cputime);
-                        utime = cputime.utime;
-                        if (cputime_le(cval, utime)) { /* about to fire */
-                                cval = jiffies_to_cputime(1);
-                        } else {
-                                cval = cputime_sub(cval, utime);
-                        }
-                }
-                spin_unlock_irq(&tsk->sighand->siglock);
-                cputime_to_timeval(cval, &value->it_value);
-                cputime_to_timeval(cinterval, &value->it_interval);
+                get_cpu_itimer(tsk, CPUCLOCK_VIRT, value);
                 break;
         case ITIMER_PROF:
-                spin_lock_irq(&tsk->sighand->siglock);
-                cval = tsk->signal->it_prof_expires;
-                cinterval = tsk->signal->it_prof_incr;
-                if (!cputime_eq(cval, cputime_zero)) {
-                        struct task_cputime times;
-                        cputime_t ptime;
-
-                        thread_group_cputimer(tsk, &times);
-                        ptime = cputime_add(times.utime, times.stime);
-                        if (cputime_le(cval, ptime)) { /* about to fire */
-                                cval = jiffies_to_cputime(1);
-                        } else {
-                                cval = cputime_sub(cval, ptime);
-                        }
-                }
-                spin_unlock_irq(&tsk->sighand->siglock);
-                cputime_to_timeval(cval, &value->it_value);
-                cputime_to_timeval(cinterval, &value->it_interval);
+                get_cpu_itimer(tsk, CPUCLOCK_PROF, value);
                 break;
         default:
                 return(-EINVAL);
@@ -128,6 +127,54 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer)
         return HRTIMER_NORESTART;
 }
 
+static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns)
+{
+        struct timespec ts;
+        s64 cpu_ns;
+
+        cputime_to_timespec(ct, &ts);
+        cpu_ns = timespec_to_ns(&ts);
+
+        return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns;
+}
+
+static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
+                           const struct itimerval *const value,
+                           struct itimerval *const ovalue)
+{
+        cputime_t cval, nval, cinterval, ninterval;
+        s64 ns_ninterval, ns_nval;
+        struct cpu_itimer *it = &tsk->signal->it[clock_id];
+
+        nval = timeval_to_cputime(&value->it_value);
+        ns_nval = timeval_to_ns(&value->it_value);
+        ninterval = timeval_to_cputime(&value->it_interval);
+        ns_ninterval = timeval_to_ns(&value->it_interval);
+
+        it->incr_error = cputime_sub_ns(ninterval, ns_ninterval);
+        it->error = cputime_sub_ns(nval, ns_nval);
+
+        spin_lock_irq(&tsk->sighand->siglock);
+
+        cval = it->expires;
+        cinterval = it->incr;
+        if (!cputime_eq(cval, cputime_zero) ||
+            !cputime_eq(nval, cputime_zero)) {
+                if (cputime_gt(nval, cputime_zero))
+                        nval = cputime_add(nval, cputime_one_jiffy);
+                set_process_cpu_timer(tsk, clock_id, &nval, &cval);
+        }
+        it->expires = nval;
+        it->incr = ninterval;
+
+        spin_unlock_irq(&tsk->sighand->siglock);
+
+        if (ovalue) {
+                cputime_to_timeval(cval, &ovalue->it_value);
+                cputime_to_timeval(cinterval, &ovalue->it_interval);
+        }
+}
+
 /*
  * Returns true if the timeval is in canonical form
  */
@@ -139,7 +186,6 @@ int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue)
         struct task_struct *tsk = current;
         struct hrtimer *timer;
         ktime_t expires;
-        cputime_t cval, cinterval, nval, ninterval;
 
         /*
          * Validate the timevals in value.
@@ -174,48 +220,10 @@ again:
                 spin_unlock_irq(&tsk->sighand->siglock);
                 break;
         case ITIMER_VIRTUAL:
-                nval = timeval_to_cputime(&value->it_value);
-                ninterval = timeval_to_cputime(&value->it_interval);
-                spin_lock_irq(&tsk->sighand->siglock);
-                cval = tsk->signal->it_virt_expires;
-                cinterval = tsk->signal->it_virt_incr;
-                if (!cputime_eq(cval, cputime_zero) ||
-                    !cputime_eq(nval, cputime_zero)) {
-                        if (cputime_gt(nval, cputime_zero))
-                                nval = cputime_add(nval,
-                                                   jiffies_to_cputime(1));
-                        set_process_cpu_timer(tsk, CPUCLOCK_VIRT,
-                                              &nval, &cval);
-                }
-                tsk->signal->it_virt_expires = nval;
-                tsk->signal->it_virt_incr = ninterval;
-                spin_unlock_irq(&tsk->sighand->siglock);
-                if (ovalue) {
-                        cputime_to_timeval(cval, &ovalue->it_value);
-                        cputime_to_timeval(cinterval, &ovalue->it_interval);
-                }
+                set_cpu_itimer(tsk, CPUCLOCK_VIRT, value, ovalue);
                 break;
         case ITIMER_PROF:
-                nval = timeval_to_cputime(&value->it_value);
-                ninterval = timeval_to_cputime(&value->it_interval);
-                spin_lock_irq(&tsk->sighand->siglock);
-                cval = tsk->signal->it_prof_expires;
-                cinterval = tsk->signal->it_prof_incr;
-                if (!cputime_eq(cval, cputime_zero) ||
-                    !cputime_eq(nval, cputime_zero)) {
-                        if (cputime_gt(nval, cputime_zero))
-                                nval = cputime_add(nval,
-                                                   jiffies_to_cputime(1));
-                        set_process_cpu_timer(tsk, CPUCLOCK_PROF,
-                                              &nval, &cval);
-                }
-                tsk->signal->it_prof_expires = nval;
-                tsk->signal->it_prof_incr = ninterval;
-                spin_unlock_irq(&tsk->sighand->siglock);
-                if (ovalue) {
-                        cputime_to_timeval(cval, &ovalue->it_value);
-                        cputime_to_timeval(cinterval, &ovalue->it_interval);
-                }
+                set_cpu_itimer(tsk, CPUCLOCK_PROF, value, ovalue);
                 break;
         default:
                 return -EINVAL;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e33a21cb9407..12161f74744e 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -14,11 +14,11 @@
  */
 void update_rlimit_cpu(unsigned long rlim_new)
 {
-        cputime_t cputime;
+        cputime_t cputime = secs_to_cputime(rlim_new);
+        struct signal_struct *const sig = current->signal;
 
-        cputime = secs_to_cputime(rlim_new);
-        if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
-            cputime_gt(current->signal->it_prof_expires, cputime)) {
+        if (cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) ||
+            cputime_gt(sig->it[CPUCLOCK_PROF].expires, cputime)) {
                 spin_lock_irq(&current->sighand->siglock);
                 set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
                 spin_unlock_irq(&current->sighand->siglock);
@@ -542,6 +542,17 @@ static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
                                              now);
 }
 
+static inline int expires_gt(cputime_t expires, cputime_t new_exp)
+{
+        return cputime_eq(expires, cputime_zero) ||
+               cputime_gt(expires, new_exp);
+}
+
+static inline int expires_le(cputime_t expires, cputime_t new_exp)
+{
+        return !cputime_eq(expires, cputime_zero) &&
+               cputime_le(expires, new_exp);
+}
 /*
  * Insert the timer on the appropriate list before any timers that
  * expire later.  This must be called with the tasklist_lock held
@@ -586,34 +597,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
                  */
 
                 if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
+                        union cpu_time_count *exp = &nt->expires;
+
                         switch (CPUCLOCK_WHICH(timer->it_clock)) {
                         default:
                                 BUG();
                         case CPUCLOCK_PROF:
-                                if (cputime_eq(p->cputime_expires.prof_exp,
-                                               cputime_zero) ||
-                                    cputime_gt(p->cputime_expires.prof_exp,
-                                               nt->expires.cpu))
-                                        p->cputime_expires.prof_exp =
-                                                nt->expires.cpu;
+                                if (expires_gt(p->cputime_expires.prof_exp,
+                                               exp->cpu))
+                                        p->cputime_expires.prof_exp = exp->cpu;
                                 break;
                         case CPUCLOCK_VIRT:
-                                if (cputime_eq(p->cputime_expires.virt_exp,
-                                               cputime_zero) ||
-                                    cputime_gt(p->cputime_expires.virt_exp,
-                                               nt->expires.cpu))
-                                        p->cputime_expires.virt_exp =
-                                                nt->expires.cpu;
+                                if (expires_gt(p->cputime_expires.virt_exp,
+                                               exp->cpu))
+                                        p->cputime_expires.virt_exp = exp->cpu;
                                 break;
                         case CPUCLOCK_SCHED:
                                 if (p->cputime_expires.sched_exp == 0 ||
-                                    p->cputime_expires.sched_exp >
-                                                        nt->expires.sched)
+                                    p->cputime_expires.sched_exp > exp->sched)
                                         p->cputime_expires.sched_exp =
-                                                nt->expires.sched;
+                                                                exp->sched;
                                 break;
                         }
                 } else {
+                        struct signal_struct *const sig = p->signal;
+                        union cpu_time_count *exp = &timer->it.cpu.expires;
+
                         /*
                          * For a process timer, set the cached expiration time.
                          */
@@ -621,30 +630,23 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
                         default:
                                 BUG();
                         case CPUCLOCK_VIRT:
-                                if (!cputime_eq(p->signal->it_virt_expires,
-                                                cputime_zero) &&
-                                    cputime_lt(p->signal->it_virt_expires,
-                                               timer->it.cpu.expires.cpu))
+                                if (expires_le(sig->it[CPUCLOCK_VIRT].expires,
+                                               exp->cpu))
                                         break;
-                                p->signal->cputime_expires.virt_exp =
-                                        timer->it.cpu.expires.cpu;
+                                sig->cputime_expires.virt_exp = exp->cpu;
                                 break;
                         case CPUCLOCK_PROF:
-                                if (!cputime_eq(p->signal->it_prof_expires,
-                                                cputime_zero) &&
-                                    cputime_lt(p->signal->it_prof_expires,
-                                               timer->it.cpu.expires.cpu))
+                                if (expires_le(sig->it[CPUCLOCK_PROF].expires,
+                                               exp->cpu))
                                         break;
-                                i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
+                                i = sig->rlim[RLIMIT_CPU].rlim_cur;
                                 if (i != RLIM_INFINITY &&
-                                    i <= cputime_to_secs(timer->it.cpu.expires.cpu))
+                                    i <= cputime_to_secs(exp->cpu))
                                         break;
-                                p->signal->cputime_expires.prof_exp =
-                                        timer->it.cpu.expires.cpu;
+                                sig->cputime_expires.prof_exp = exp->cpu;
                                 break;
                         case CPUCLOCK_SCHED:
-                                p->signal->cputime_expires.sched_exp =
-                                        timer->it.cpu.expires.sched;
+                                sig->cputime_expires.sched_exp = exp->sched;
                                 break;
                         }
                 }
@@ -1071,6 +1073,36 @@ static void stop_process_timers(struct task_struct *tsk)
         spin_unlock_irqrestore(&cputimer->lock, flags);
 }
 
+static u32 onecputick;
+
+static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
+                             cputime_t *expires, cputime_t cur_time, int signo)
+{
+        if (cputime_eq(it->expires, cputime_zero))
+                return;
+
+        if (cputime_ge(cur_time, it->expires)) {
+                if (!cputime_eq(it->incr, cputime_zero)) {
+                        it->expires = cputime_add(it->expires, it->incr);
+                        it->error += it->incr_error;
+                        if (it->error >= onecputick) {
+                                it->expires = cputime_sub(it->expires,
+                                                          cputime_one_jiffy);
+                                it->error -= onecputick;
+                        }
+                } else
+                        it->expires = cputime_zero;
+
+                __group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+        }
+
+        if (!cputime_eq(it->expires, cputime_zero) &&
+            (cputime_eq(*expires, cputime_zero) ||
+             cputime_lt(it->expires, *expires))) {
+                *expires = it->expires;
+        }
+}
+
 /*
  * Check for any per-thread CPU timers that have fired and move them
  * off the tsk->*_timers list onto the firing list.  Per-thread timers
@@ -1090,10 +1122,10 @@ static void check_process_timers(struct task_struct *tsk,
          * Don't sample the current process CPU clocks if there are no timers.
          */
         if (list_empty(&timers[CPUCLOCK_PROF]) &&
-            cputime_eq(sig->it_prof_expires, cputime_zero) &&
+            cputime_eq(sig->it[CPUCLOCK_PROF].expires, cputime_zero) &&
             sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
             list_empty(&timers[CPUCLOCK_VIRT]) &&
-            cputime_eq(sig->it_virt_expires, cputime_zero) &&
+            cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
             list_empty(&timers[CPUCLOCK_SCHED])) {
                 stop_process_timers(tsk);
                 return;
@@ -1153,38 +1185,11 @@ static void check_process_timers(struct task_struct *tsk,
         /*
          * Check for the special case process timers.
          */
-        if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
-                if (cputime_ge(ptime, sig->it_prof_expires)) {
-                        /* ITIMER_PROF fires and reloads.  */
-                        sig->it_prof_expires = sig->it_prof_incr;
-                        if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
-                                sig->it_prof_expires = cputime_add(
-                                        sig->it_prof_expires, ptime);
-                        }
-                        __group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk);
-                }
-                if (!cputime_eq(sig->it_prof_expires, cputime_zero) &&
-                    (cputime_eq(prof_expires, cputime_zero) ||
-                     cputime_lt(sig->it_prof_expires, prof_expires))) {
-                        prof_expires = sig->it_prof_expires;
-                }
-        }
-        if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
-                if (cputime_ge(utime, sig->it_virt_expires)) {
-                        /* ITIMER_VIRTUAL fires and reloads.  */
-                        sig->it_virt_expires = sig->it_virt_incr;
-                        if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
-                                sig->it_virt_expires = cputime_add(
-                                        sig->it_virt_expires, utime);
-                        }
-                        __group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk);
-                }
-                if (!cputime_eq(sig->it_virt_expires, cputime_zero) &&
-                    (cputime_eq(virt_expires, cputime_zero) ||
-                     cputime_lt(sig->it_virt_expires, virt_expires))) {
-                        virt_expires = sig->it_virt_expires;
-                }
-        }
+        check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &prof_expires, ptime,
+                         SIGPROF);
+        check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
+                         SIGVTALRM);
+
         if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
                 unsigned long psecs = cputime_to_secs(ptime);
                 cputime_t x;
@@ -1457,7 +1462,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
                 if (!cputime_eq(*oldval, cputime_zero)) {
                         if (cputime_le(*oldval, now.cpu)) {
                                 /* Just about to fire. */
-                                *oldval = jiffies_to_cputime(1);
+                                *oldval = cputime_one_jiffy;
                         } else {
                                 *oldval = cputime_sub(*oldval, now.cpu);
                         }
@@ -1703,10 +1708,15 @@ static __init int init_posix_cpu_timers(void)
                 .nsleep = thread_cpu_nsleep,
                 .nsleep_restart = thread_cpu_nsleep_restart,
         };
+        struct timespec ts;
 
         register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
         register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
 
+        cputime_to_timespec(cputime_one_jiffy, &ts);
+        onecputick = ts.tv_nsec;
+        WARN_ON(ts.tv_sec != 0);
+
         return 0;
 }
 __initcall(init_posix_cpu_timers);
diff --git a/kernel/sched.c b/kernel/sched.c
index 1b59e265273b..8f977d5cc515 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5031,17 +5031,16 @@ void account_idle_time(cputime_t cputime)
  */
 void account_process_tick(struct task_struct *p, int user_tick)
 {
-        cputime_t one_jiffy = jiffies_to_cputime(1);
-        cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+        cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
         struct rq *rq = this_rq();
 
         if (user_tick)
-                account_user_time(p, one_jiffy, one_jiffy_scaled);
+                account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
         else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
-                account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+                account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
                                     one_jiffy_scaled);
         else
-                account_idle_time(one_jiffy);
+                account_idle_time(cputime_one_jiffy);
 }
 
 /*