From 6f0d5c390e4206dcb3804a5072a048fdb7d2b428 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 19 Aug 2008 12:33:03 +0200 Subject: sched: rt-bandwidth accounting fix It fixes an accounting bug where we would continue accumulating runtime even though the bandwidth control is disabled. This would lead to very long throttle periods once bandwidth control gets turned on again. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel/sched_rt.c') diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 998ba54b4543..77340b04a538 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -438,9 +438,6 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) { u64 runtime = sched_rt_runtime(rt_rq); - if (runtime == RUNTIME_INF) - return 0; - if (rt_rq->rt_throttled) return rt_rq_throttled(rt_rq); @@ -491,9 +488,11 @@ static void update_curr_rt(struct rq *rq) rt_rq = rt_rq_of_se(rt_se); spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_time += delta_exec; - if (sched_rt_runtime_exceeded(rt_rq)) - resched_task(curr); + if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { + rt_rq->rt_time += delta_exec; + if (sched_rt_runtime_exceeded(rt_rq)) + resched_task(curr); + } spin_unlock(&rt_rq->rt_runtime_lock); } } -- cgit v1.2.3 From 0b148fa04852859972abbf848177b92daeef138a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 19 Aug 2008 12:33:04 +0200 Subject: sched: rt-bandwidth group disable fixes More extensive disable of bandwidth control. It allows sysctl_sched_rt_runtime to disable full group bandwidth control. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched.c | 9 ++++++++- kernel/sched_rt.c | 5 ++++- 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'kernel/sched_rt.c') diff --git a/kernel/sched.c b/kernel/sched.c index 9a1ddb84e26d..c1bee5fb8154 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -204,11 +204,13 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; } +static inline int rt_bandwidth_enabled(void); + static void start_rt_bandwidth(struct rt_bandwidth *rt_b) { ktime_t now; - if (rt_b->rt_runtime == RUNTIME_INF) + if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF) return; if (hrtimer_active(&rt_b->rt_period_timer)) @@ -839,6 +841,11 @@ static inline u64 global_rt_runtime(void) return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; } +static inline int rt_bandwidth_enabled(void) +{ + return sysctl_sched_rt_runtime >= 0; +} + #ifndef prepare_arch_switch # define prepare_arch_switch(next) do { } while (0) #endif diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 77340b04a538..94daace5ee15 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -386,7 +386,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) int i, idle = 1; cpumask_t span; - if (rt_b->rt_runtime == RUNTIME_INF) + if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) return 1; span = sched_rt_period_mask(); @@ -484,6 +484,9 @@ static void update_curr_rt(struct rq *rq) curr->se.exec_start = rq->clock; cpuacct_charge(curr, delta_exec); + if (!rt_bandwidth_enabled()) + return; + for_each_sched_rt_entity(rt_se) { rt_rq = rt_rq_of_se(rt_se); -- cgit v1.2.3 From f3ade837808121ff8bab9c56725f4fe40ec85a56 Mon Sep 17 00:00:00 2001 From: John Blackwood Date: Tue, 26 Aug 2008 15:09:43 -0400 Subject: sched: fix sched_rt_rq_enqueue() resched idle When sysctl_sched_rt_runtime is set to something other than -1 and the CONFIG_RT_GROUP_SCHED kernel parameter is NOT enabled, we get into a state where we see one or more CPUs idling forvever even though there are real-time tasks in their rt runqueue that are able to run (no longer throttled). The sequence is: - A real-time task is running when the timer sets the rt runqueue to throttled, and the rt task is resched_task()ed and switched out, and idle is switched in since there are no non-rt tasks to run on that cpu. - Eventually the do_sched_rt_period_timer() runs and un-throttles the rt runqueue, but we just exit the timer interrupt and go back to executing the idle task in the idle loop forever. If we change the sched_rt_rq_enqueue() routine to use some of the code from the CONFIG_RT_GROUP_SCHED enabled version of this same routine and resched_task() the currently executing task (idle in our case) if it is a lower priority task than the higher rt task in the now un-throttled runqueue, the problem is no longer observed. Signed-off-by: John Blackwood Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/sched_rt.c') diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 998ba54b4543..07d9b3307907 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -199,6 +199,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { + if (rt_rq->rt_nr_running) + resched_task(rq_of_rt_rq(rt_rq)->curr); } static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) -- cgit v1.2.3 From cc2991cf15ae92fa30b3ea9f56a8a5a337bd33c7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 19 Aug 2008 12:33:03 +0200 Subject: sched: rt-bandwidth accounting fix It fixes an accounting bug where we would continue accumulating runtime even though the bandwidth control is disabled. This would lead to very long throttle periods once bandwidth control gets turned on again. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel/sched_rt.c') diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 07d9b3307907..552310798dad 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -440,9 +440,6 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) { u64 runtime = sched_rt_runtime(rt_rq); - if (runtime == RUNTIME_INF) - return 0; - if (rt_rq->rt_throttled) return rt_rq_throttled(rt_rq); @@ -493,9 +490,11 @@ static void update_curr_rt(struct rq *rq) rt_rq = rt_rq_of_se(rt_se); spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_time += delta_exec; - if (sched_rt_runtime_exceeded(rt_rq)) - resched_task(curr); + if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { + rt_rq->rt_time += delta_exec; + if (sched_rt_runtime_exceeded(rt_rq)) + resched_task(curr); + } spin_unlock(&rt_rq->rt_runtime_lock); } } -- cgit v1.2.3 From baf25731e54d06eb13dc4eda78c6dc7da4ce84e8 Mon Sep 17 00:00:00 2001 From: "Zhang, Yanmin" Date: Tue, 9 Sep 2008 11:26:33 +0800 Subject: sched: fix 2.6.27-rc5 couldn't boot on tulsa machine randomly On my tulsa x86-64 machine, kernel 2.6.25-rc5 couldn't boot randomly. Basically, function __enable_runtime forgets to reset rt_rq->rt_throttled to 0. When every cpu is up, per-cpu migration_thread is created and it runs very fast, sometimes to mark the corresponding rt_rq->rt_throttled to 1 very quickly. After all cpus are up, with below calling chain: sched_init_smp => arch_init_sched_domains => build_sched_domains => ... => cpu_attach_domain => rq_attach_root => set_rq_online => ... => _enable_runtime _enable_runtime is called against every rt_rq again, so rt_rq->rt_time is reset to 0, but rt_rq->rt_throttled might be still 1. Later on function do_sched_rt_period_timer couldn't reset it, and all RT tasks couldn't be scheduled to run on that cpu. here is RT task migration_thread which is woken up when a task is migrated to another cpu. Below patch fixes it against 2.6.27-rc5. Signed-off-by: Zhang Yanmin Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/sched_rt.c') diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 552310798dad..1113157b2058 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -350,6 +350,7 @@ static void __enable_runtime(struct rq *rq) spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_runtime = rt_b->rt_runtime; rt_rq->rt_time = 0; + rt_rq->rt_throttled = 0; spin_unlock(&rt_rq->rt_runtime_lock); spin_unlock(&rt_b->rt_runtime_lock); } -- cgit v1.2.3 From f06febc96ba8e0af80bcc3eaec0a109e88275fac Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: timers: fix itimer/many thread hang Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar --- fs/binfmt_elf.c | 19 +- fs/proc/array.c | 8 +- include/linux/posix-timers.h | 2 + include/linux/sched.h | 257 +++++++++++++++++++++-- include/linux/time.h | 3 + kernel/compat.c | 53 ++--- kernel/exit.c | 19 +- kernel/fork.c | 88 ++++---- kernel/itimer.c | 33 +-- kernel/posix-cpu-timers.c | 471 +++++++++++++++++++++++-------------------- kernel/sched.c | 53 ++++- kernel/sched_fair.c | 1 + kernel/sched_rt.c | 4 +- kernel/signal.c | 8 +- kernel/sys.c | 75 +++---- security/selinux/hooks.c | 9 +- 16 files changed, 677 insertions(+), 426 deletions(-) (limited to 'kernel/sched_rt.c') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 655ed8d30a86..a8635f637038 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1333,20 +1333,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { + struct task_cputime cputime; + /* - * This is the record for the group leader. Add in the - * cumulative times of previous dead threads. This total - * won't include the time of each live thread whose state - * is included in the core dump. The final total reported - * to our parent process when it calls wait4 will include - * those sums as well as the little bit more time it takes - * this and each other thread to finish dying after the - * core dump synchronization phase. + * This is the record for the group leader. It shows the + * group-wide total, not its individual thread total. */ - cputime_to_timeval(cputime_add(p->utime, p->signal->utime), - &prstatus->pr_utime); - cputime_to_timeval(cputime_add(p->stime, p->signal->stime), - &prstatus->pr_stime); + thread_group_cputime(p, &cputime); + cputime_to_timeval(cputime.utime, &prstatus->pr_utime); + cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { cputime_to_timeval(p->utime, &prstatus->pr_utime); cputime_to_timeval(p->stime, &prstatus->pr_stime); diff --git a/fs/proc/array.c b/fs/proc/array.c index 71c9be59c9c2..933953c4e407 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -395,20 +395,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* add up live thread stats at the group level */ if (whole) { + struct task_cputime cputime; struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, task_utime(t)); - stime = cputime_add(stime, task_stime(t)); gtime = cputime_add(gtime, task_gtime(t)); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - utime = cputime_add(utime, sig->utime); - stime = cputime_add(stime, sig->stime); + thread_group_cputime(task, &cputime); + utime = cputime.utime; + stime = cputime.stime; gtime = cputime_add(gtime, sig->gtime); } diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index a7dd38f30ade..f9d8e9e94e9b 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -115,4 +115,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, long clock_nanosleep_restart(struct restart_block *restart_block); +void update_rlimit_cpu(unsigned long rlim_new); + #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 3d9120c5ad15..26d7a5f2d0ba 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -425,6 +425,45 @@ struct pacct_struct { unsigned long ac_minflt, ac_majflt; }; +/** + * struct task_cputime - collected CPU time counts + * @utime: time spent in user mode, in &cputime_t units + * @stime: time spent in kernel mode, in &cputime_t units + * @sum_exec_runtime: total time spent on the CPU, in nanoseconds + * + * This structure groups together three kinds of CPU time that are + * tracked for threads and thread groups. Most things considering + * CPU time want to group these counts together and treat all three + * of them in parallel. + */ +struct task_cputime { + cputime_t utime; + cputime_t stime; + unsigned long long sum_exec_runtime; +}; +/* Alternate field names when used to cache expirations. */ +#define prof_exp stime +#define virt_exp utime +#define sched_exp sum_exec_runtime + +/** + * struct thread_group_cputime - thread group interval timer counts + * @totals: thread group interval timers; substructure for + * uniprocessor kernel, per-cpu for SMP kernel. + * + * This structure contains the version of task_cputime, above, that is + * used for thread group CPU clock calculations. + */ +#ifdef CONFIG_SMP +struct thread_group_cputime { + struct task_cputime *totals; +}; +#else +struct thread_group_cputime { + struct task_cputime totals; +}; +#endif + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -470,6 +509,17 @@ struct signal_struct { cputime_t it_prof_expires, it_virt_expires; cputime_t it_prof_incr, it_virt_incr; + /* + * Thread group totals for process CPU clocks. + * See thread_group_cputime(), et al, for details. + */ + struct thread_group_cputime cputime; + + /* Earliest-expiration cache. */ + struct task_cputime cputime_expires; + + struct list_head cpu_timers[3]; + /* job control IDs */ /* @@ -500,7 +550,7 @@ struct signal_struct { * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ - cputime_t utime, stime, cutime, cstime; + cputime_t cutime, cstime; cputime_t gtime; cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -508,14 +558,6 @@ struct signal_struct { unsigned long inblock, oublock, cinblock, coublock; struct task_io_accounting ioac; - /* - * Cumulative ns of scheduled CPU time for dead threads in the - * group, not including a zombie group leader. (This only differs - * from jiffies_to_ns(utime + stime) if sched_clock uses something - * other than jiffies.) - */ - unsigned long long sum_sched_runtime; - /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs @@ -527,8 +569,6 @@ struct signal_struct { */ struct rlimit rlim[RLIM_NLIMITS]; - struct list_head cpu_timers[3]; - /* keep the process-shared keyrings here so that they do the right * thing in threads created with CLONE_THREAD */ #ifdef CONFIG_KEYS @@ -1134,8 +1174,7 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; - cputime_t it_prof_expires, it_virt_expires; - unsigned long long it_sched_expires; + struct task_cputime cputime_expires; struct list_head cpu_timers[3]; /* process credentials */ @@ -1585,6 +1624,7 @@ extern unsigned long long cpu_clock(int cpu); extern unsigned long long task_sched_runtime(struct task_struct *task); +extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP @@ -2081,6 +2121,197 @@ static inline int spin_needbreak(spinlock_t *lock) #endif } +/* + * Thread group CPU time accounting. + */ +#ifdef CONFIG_SMP + +extern int thread_group_cputime_alloc_smp(struct task_struct *); +extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *); + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals = NULL; +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *new) +{ + if (curr->signal->cputime.totals) + return 0; + return thread_group_cputime_alloc_smp(curr); +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ + free_percpu(sig->cputime.totals); +} + +/** + * thread_group_cputime - Sum the thread group time fields across all CPUs. + * + * This is a wrapper for the real routine, thread_group_cputime_smp(). See + * that routine for details. + */ +static inline void thread_group_cputime( + struct task_struct *tsk, + struct task_cputime *times) +{ + thread_group_cputime_smp(tsk, times); +} + +/** + * thread_group_cputime_account_user - Maintain utime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the utime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_system - Maintain stime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the stime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a + * thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of that structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} + +#else /* CONFIG_SMP */ + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals.utime = cputime_zero; + sig->cputime.totals.stime = cputime_zero; + sig->cputime.totals.sum_exec_runtime = 0; +} + +static inline int thread_group_cputime_alloc(struct task_struct *tsk) +{ + return 0; +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *tsk) +{ +} + +static inline void thread_group_cputime(struct task_struct *tsk, + struct task_cputime *cputime) +{ + *cputime = tsk->signal->cputime.totals; +} + +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); +} + +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); +} + +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + tgtimes->totals->sum_exec_runtime += ns; +} + +#endif /* CONFIG_SMP */ + +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_user(&sig->cputime, cputime); +} + +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_system(&sig->cputime, cputime); +} + +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_exec_runtime(&sig->cputime, ns); +} + /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. diff --git a/include/linux/time.h b/include/linux/time.h index e15206a7e82e..1b70b3c293e9 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -125,6 +125,9 @@ extern int timekeeping_valid_for_hres(void); extern void update_wall_time(void); extern void update_xtime_cache(u64 nsec); +struct tms; +extern void do_sys_times(struct tms *); + /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted diff --git a/kernel/compat.c b/kernel/compat.c index 32c254a8ab9a..72650e39b3e6 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -150,49 +151,23 @@ asmlinkage long compat_sys_setitimer(int which, return 0; } +static compat_clock_t clock_t_to_compat_clock_t(clock_t x) +{ + return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); +} + asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { + struct tms tms; struct compat_tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - read_lock(&tasklist_lock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - /* - * While we have tasklist_lock read-locked, no dying thread - * can be updating current->signal->[us]time. Instead, - * we got their counts included in the live thread loop. - * However, another thread can come in right now and - * do a wait call that updates current->signal->c[us]time. - * To make sure we always see that pair updated atomically, - * we take the siglock around fetching them. - */ - spin_lock_irq(&tsk->sighand->siglock); - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); - - tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime)); - tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime)); - tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime)); - tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime)); + + do_sys_times(&tms); + /* Convert our struct tms to the compat version. */ + tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); + tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); + tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); + tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } diff --git a/kernel/exit.c b/kernel/exit.c index 16395644a98f..40036ac04271 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -112,8 +112,6 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, task_utime(tsk)); - sig->stime = cputime_add(sig->stime, task_stime(tsk)); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -122,7 +120,6 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -1294,6 +1291,7 @@ static int wait_task_zombie(struct task_struct *p, int options, if (likely(!traced)) { struct signal_struct *psig; struct signal_struct *sig; + struct task_cputime cputime; /* * The resource counters for the group leader are in its @@ -1309,20 +1307,23 @@ static int wait_task_zombie(struct task_struct *p, int options, * need to protect the access to p->parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * We use thread_group_cputime() to get times for the thread + * group, which consolidates times for all threads in the + * group including the group leader. */ spin_lock_irq(&p->parent->sighand->siglock); psig = p->parent->signal; sig = p->signal; + thread_group_cputime(p, &cputime); psig->cutime = cputime_add(psig->cutime, - cputime_add(p->utime, - cputime_add(sig->utime, - sig->cutime))); + cputime_add(cputime.utime, + sig->cutime)); psig->cstime = cputime_add(psig->cstime, - cputime_add(p->stime, - cputime_add(sig->stime, - sig->cstime))); + cputime_add(cputime.stime, + sig->cstime)); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, diff --git a/kernel/fork.c b/kernel/fork.c index 7ce2ebe84796..a8ac2efb8e30 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -759,15 +759,44 @@ void __cleanup_sighand(struct sighand_struct *sighand) kmem_cache_free(sighand_cachep, sighand); } + +/* + * Initialize POSIX timer handling for a thread group. + */ +static void posix_cpu_timers_init_group(struct signal_struct *sig) +{ + /* Thread group counters. */ + 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; + + /* Cached expiration times. */ + sig->cputime_expires.prof_exp = cputime_zero; + sig->cputime_expires.virt_exp = cputime_zero; + sig->cputime_expires.sched_exp = 0; + + /* The timer lists. */ + INIT_LIST_HEAD(&sig->cpu_timers[0]); + INIT_LIST_HEAD(&sig->cpu_timers[1]); + INIT_LIST_HEAD(&sig->cpu_timers[2]); +} + static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; int ret; if (clone_flags & CLONE_THREAD) { - atomic_inc(¤t->signal->count); - atomic_inc(¤t->signal->live); - return 0; + ret = thread_group_cputime_clone_thread(current, tsk); + if (likely(!ret)) { + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); + } + return ret; } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; @@ -795,15 +824,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - 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->leader = 0; /* session leadership doesn't inherit */ sig->tty_old_pgrp = NULL; - sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; + sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; @@ -820,14 +844,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); - if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * New sole thread in the process gets an expiry time - * of the whole CPU time limit. - */ - tsk->it_prof_expires = - secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); - } + posix_cpu_timers_init_group(sig); + acct_init_pacct(&sig->pacct); tty_audit_fork(sig); @@ -837,6 +855,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_signal(struct signal_struct *sig) { + thread_group_cputime_free(sig); exit_thread_group_keys(sig); kmem_cache_free(signal_cachep, sig); } @@ -885,6 +904,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p) } #endif /* CONFIG_MM_OWNER */ +/* + * Initialize POSIX timer handling for a single task. + */ +static void posix_cpu_timers_init(struct task_struct *tsk) +{ + tsk->cputime_expires.prof_exp = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; + tsk->cputime_expires.sched_exp = 0; + INIT_LIST_HEAD(&tsk->cpu_timers[0]); + INIT_LIST_HEAD(&tsk->cpu_timers[1]); + INIT_LIST_HEAD(&tsk->cpu_timers[2]); +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -995,12 +1027,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, task_io_accounting_init(&p->ioac); acct_clear_integrals(p); - p->it_virt_expires = cputime_zero; - p->it_prof_expires = cputime_zero; - p->it_sched_expires = 0; - INIT_LIST_HEAD(&p->cpu_timers[0]); - INIT_LIST_HEAD(&p->cpu_timers[1]); - INIT_LIST_HEAD(&p->cpu_timers[2]); + posix_cpu_timers_init(p); p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); @@ -1201,21 +1228,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); - - if (!cputime_eq(current->signal->it_virt_expires, - cputime_zero) || - !cputime_eq(current->signal->it_prof_expires, - cputime_zero) || - current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY || - !list_empty(¤t->signal->cpu_timers[0]) || - !list_empty(¤t->signal->cpu_timers[1]) || - !list_empty(¤t->signal->cpu_timers[2])) { - /* - * Have child wake up on its first tick to check - * for process CPU timers. - */ - p->it_prof_expires = jiffies_to_cputime(1); - } } if (likely(p->pid)) { diff --git a/kernel/itimer.c b/kernel/itimer.c index ab982747d9bd..db7c358b9a02 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value) spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: - read_lock(&tasklist_lock); 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_struct *t = tsk; - cputime_t utime = tsk->signal->utime; - do { - utime = cputime_add(utime, t->utime); - t = next_thread(t); - } while (t != tsk); + struct task_cputime cputime; + cputime_t utime; + + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; if (cputime_le(cval, utime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; case ITIMER_PROF: - read_lock(&tasklist_lock); 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_struct *t = tsk; - cputime_t ptime = cputime_add(tsk->signal->utime, - tsk->signal->stime); - do { - ptime = cputime_add(ptime, - cputime_add(t->utime, - t->stime)); - t = next_thread(t); - } while (t != tsk); + struct task_cputime times; + cputime_t ptime; + + thread_group_cputime(tsk, ×); + ptime = cputime_add(times.utime, times.stime); if (cputime_le(cval, ptime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; @@ -185,7 +176,6 @@ again: case ITIMER_VIRTUAL: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; @@ -200,7 +190,6 @@ again: tsk->signal->it_virt_expires = nval; tsk->signal->it_virt_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); @@ -209,7 +198,6 @@ again: case ITIMER_PROF: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; @@ -224,7 +212,6 @@ again: tsk->signal->it_prof_expires = nval; tsk->signal->it_prof_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index c42a03aef36f..dba1c334c3e8 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -8,6 +8,99 @@ #include #include +#ifdef CONFIG_SMP +/* + * Allocate the thread_group_cputime structure appropriately for SMP kernels + * and fill in the current values of the fields. Called from copy_signal() + * via thread_group_cputime_clone_thread() when adding a second or subsequent + * thread to a thread group. Assumes interrupts are enabled when called. + */ +int thread_group_cputime_alloc_smp(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct task_cputime *cputime; + + /* + * If we have multiple threads and we don't already have a + * per-CPU task_cputime struct, allocate one and fill it in with + * the times accumulated so far. + */ + if (sig->cputime.totals) + return 0; + cputime = alloc_percpu(struct task_cputime); + if (cputime == NULL) + return -ENOMEM; + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + if (sig->cputime.totals) { + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + free_percpu(cputime); + return 0; + } + sig->cputime.totals = cputime; + cputime = per_cpu_ptr(sig->cputime.totals, get_cpu()); + cputime->utime = tsk->utime; + cputime->stime = tsk->stime; + cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; + put_cpu_no_resched(); + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + return 0; +} + +/** + * thread_group_cputime_smp - Sum the thread group time fields across all CPUs. + * + * @tsk: The task we use to identify the thread group. + * @times: task_cputime structure in which we return the summed fields. + * + * Walk the list of CPUs to sum the per-CPU time fields in the thread group + * time structure. + */ +void thread_group_cputime_smp( + struct task_struct *tsk, + struct task_cputime *times) +{ + struct signal_struct *sig; + int i; + struct task_cputime *tot; + + sig = tsk->signal; + if (unlikely(!sig) || !sig->cputime.totals) { + times->utime = tsk->utime; + times->stime = tsk->stime; + times->sum_exec_runtime = tsk->se.sum_exec_runtime; + return; + } + times->stime = times->utime = cputime_zero; + times->sum_exec_runtime = 0; + for_each_possible_cpu(i) { + tot = per_cpu_ptr(tsk->signal->cputime.totals, i); + times->utime = cputime_add(times->utime, tot->utime); + times->stime = cputime_add(times->stime, tot->stime); + times->sum_exec_runtime += tot->sum_exec_runtime; + } +} + +#endif /* CONFIG_SMP */ + +/* + * Called after updating RLIMIT_CPU to set timer expiration if necessary. + */ +void update_rlimit_cpu(unsigned long rlim_new) +{ + cputime_t cputime; + + cputime = secs_to_cputime(rlim_new); + if (cputime_eq(current->signal->it_prof_expires, cputime_zero) || + cputime_lt(current->signal->it_prof_expires, cputime)) { + spin_lock_irq(¤t->sighand->siglock); + set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); + spin_unlock_irq(¤t->sighand->siglock); + } +} + static int check_clock(const clockid_t which_clock) { int error = 0; @@ -158,10 +251,6 @@ static inline cputime_t virt_ticks(struct task_struct *p) { return p->utime; } -static inline unsigned long long sched_ns(struct task_struct *p) -{ - return task_sched_runtime(p); -} int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp) { @@ -211,7 +300,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, cpu->cpu = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = sched_ns(p); + cpu->sched = task_sched_runtime(p); break; } return 0; @@ -226,31 +315,20 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, struct task_struct *p, union cpu_time_count *cpu) { - struct task_struct *t = p; - switch (clock_idx) { + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + switch (clock_idx) { default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = cputime_add(p->signal->utime, p->signal->stime); - do { - cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t)); - t = next_thread(t); - } while (t != p); + cpu->cpu = cputime_add(cputime.utime, cputime.stime); break; case CPUCLOCK_VIRT: - cpu->cpu = p->signal->utime; - do { - cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t)); - t = next_thread(t); - } while (t != p); + cpu->cpu = cputime.utime; break; case CPUCLOCK_SCHED: - cpu->sched = p->signal->sum_sched_runtime; - /* Add in each other live thread. */ - while ((t = next_thread(t)) != p) { - cpu->sched += t->se.sum_exec_runtime; - } - cpu->sched += sched_ns(p); + cpu->sched = thread_group_sched_runtime(p); break; } return 0; @@ -471,80 +549,11 @@ void posix_cpu_timers_exit(struct task_struct *tsk) } void posix_cpu_timers_exit_group(struct task_struct *tsk) { - cleanup_timers(tsk->signal->cpu_timers, - cputime_add(tsk->utime, tsk->signal->utime), - cputime_add(tsk->stime, tsk->signal->stime), - tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime); -} - - -/* - * Set the expiry times of all the threads in the process so one of them - * will go off before the process cumulative expiry total is reached. - */ -static void process_timer_rebalance(struct task_struct *p, - unsigned int clock_idx, - union cpu_time_count expires, - union cpu_time_count val) -{ - cputime_t ticks, left; - unsigned long long ns, nsleft; - struct task_struct *t = p; - unsigned int nthreads = atomic_read(&p->signal->live); - - if (!nthreads) - return; + struct task_cputime cputime; - switch (clock_idx) { - default: - BUG(); - break; - case CPUCLOCK_PROF: - left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), - nthreads); - do { - if (likely(!(t->flags & PF_EXITING))) { - ticks = cputime_add(prof_ticks(t), left); - if (cputime_eq(t->it_prof_expires, - cputime_zero) || - cputime_gt(t->it_prof_expires, ticks)) { - t->it_prof_expires = ticks; - } - } - t = next_thread(t); - } while (t != p); - break; - case CPUCLOCK_VIRT: - left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), - nthreads); - do { - if (likely(!(t->flags & PF_EXITING))) { - ticks = cputime_add(virt_ticks(t), left); - if (cputime_eq(t->it_virt_expires, - cputime_zero) || - cputime_gt(t->it_virt_expires, ticks)) { - t->it_virt_expires = ticks; - } - } - t = next_thread(t); - } while (t != p); - break; - case CPUCLOCK_SCHED: - nsleft = expires.sched - val.sched; - do_div(nsleft, nthreads); - nsleft = max_t(unsigned long long, nsleft, 1); - do { - if (likely(!(t->flags & PF_EXITING))) { - ns = t->se.sum_exec_runtime + nsleft; - if (t->it_sched_expires == 0 || - t->it_sched_expires > ns) { - t->it_sched_expires = ns; - } - } - t = next_thread(t); - } while (t != p); - break; - } + thread_group_cputime(tsk, &cputime); + cleanup_timers(tsk->signal->cpu_timers, + cputime.utime, cputime.stime, cputime.sum_exec_runtime); } static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) @@ -608,29 +617,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) default: BUG(); case CPUCLOCK_PROF: - if (cputime_eq(p->it_prof_expires, + if (cputime_eq(p->cputime_expires.prof_exp, cputime_zero) || - cputime_gt(p->it_prof_expires, + cputime_gt(p->cputime_expires.prof_exp, nt->expires.cpu)) - p->it_prof_expires = nt->expires.cpu; + p->cputime_expires.prof_exp = + nt->expires.cpu; break; case CPUCLOCK_VIRT: - if (cputime_eq(p->it_virt_expires, + if (cputime_eq(p->cputime_expires.virt_exp, cputime_zero) || - cputime_gt(p->it_virt_expires, + cputime_gt(p->cputime_expires.virt_exp, nt->expires.cpu)) - p->it_virt_expires = nt->expires.cpu; + p->cputime_expires.virt_exp = + nt->expires.cpu; break; case CPUCLOCK_SCHED: - if (p->it_sched_expires == 0 || - p->it_sched_expires > nt->expires.sched) - p->it_sched_expires = nt->expires.sched; + if (p->cputime_expires.sched_exp == 0 || + p->cputime_expires.sched_exp > + nt->expires.sched) + p->cputime_expires.sched_exp = + nt->expires.sched; break; } } else { /* - * For a process timer, we must balance - * all the live threads' expirations. + * For a process timer, set the cached expiration time. */ switch (CPUCLOCK_WHICH(timer->it_clock)) { default: @@ -641,7 +653,9 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) cputime_lt(p->signal->it_virt_expires, timer->it.cpu.expires.cpu)) break; - goto rebalance; + p->signal->cputime_expires.virt_exp = + timer->it.cpu.expires.cpu; + break; case CPUCLOCK_PROF: if (!cputime_eq(p->signal->it_prof_expires, cputime_zero) && @@ -652,13 +666,12 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) if (i != RLIM_INFINITY && i <= cputime_to_secs(timer->it.cpu.expires.cpu)) break; - goto rebalance; + p->signal->cputime_expires.prof_exp = + timer->it.cpu.expires.cpu; + break; case CPUCLOCK_SCHED: - rebalance: - process_timer_rebalance( - timer->it.cpu.task, - CPUCLOCK_WHICH(timer->it_clock), - timer->it.cpu.expires, now); + p->signal->cputime_expires.sched_exp = + timer->it.cpu.expires.sched; break; } } @@ -969,13 +982,13 @@ static void check_thread_timers(struct task_struct *tsk, struct signal_struct *const sig = tsk->signal; maxfire = 20; - tsk->it_prof_expires = cputime_zero; + tsk->cputime_expires.prof_exp = cputime_zero; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) { - tsk->it_prof_expires = t->expires.cpu; + tsk->cputime_expires.prof_exp = t->expires.cpu; break; } t->firing = 1; @@ -984,13 +997,13 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->it_virt_expires = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) { - tsk->it_virt_expires = t->expires.cpu; + tsk->cputime_expires.virt_exp = t->expires.cpu; break; } t->firing = 1; @@ -999,13 +1012,13 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->it_sched_expires = 0; + tsk->cputime_expires.sched_exp = 0; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) { - tsk->it_sched_expires = t->expires.sched; + tsk->cputime_expires.sched_exp = t->expires.sched; break; } t->firing = 1; @@ -1055,10 +1068,10 @@ static void check_process_timers(struct task_struct *tsk, { int maxfire; struct signal_struct *const sig = tsk->signal; - cputime_t utime, stime, ptime, virt_expires, prof_expires; + cputime_t utime, ptime, virt_expires, prof_expires; unsigned long long sum_sched_runtime, sched_expires; - struct task_struct *t; struct list_head *timers = sig->cpu_timers; + struct task_cputime cputime; /* * Don't sample the current process CPU clocks if there are no timers. @@ -1074,18 +1087,10 @@ static void check_process_timers(struct task_struct *tsk, /* * Collect the current process totals. */ - utime = sig->utime; - stime = sig->stime; - sum_sched_runtime = sig->sum_sched_runtime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - sum_sched_runtime += t->se.sum_exec_runtime; - t = next_thread(t); - } while (t != tsk); - ptime = cputime_add(utime, stime); - + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; + ptime = cputime_add(utime, cputime.stime); + sum_sched_runtime = cputime.sum_exec_runtime; maxfire = 20; prof_expires = cputime_zero; while (!list_empty(timers)) { @@ -1193,60 +1198,18 @@ static void check_process_timers(struct task_struct *tsk, } } - if (!cputime_eq(prof_expires, cputime_zero) || - !cputime_eq(virt_expires, cputime_zero) || - sched_expires != 0) { - /* - * Rebalance the threads' expiry times for the remaining - * process CPU timers. - */ - - cputime_t prof_left, virt_left, ticks; - unsigned long long sched_left, sched; - const unsigned int nthreads = atomic_read(&sig->live); - - if (!nthreads) - return; - - prof_left = cputime_sub(prof_expires, utime); - prof_left = cputime_sub(prof_left, stime); - prof_left = cputime_div_non_zero(prof_left, nthreads); - virt_left = cputime_sub(virt_expires, utime); - virt_left = cputime_div_non_zero(virt_left, nthreads); - if (sched_expires) { - sched_left = sched_expires - sum_sched_runtime; - do_div(sched_left, nthreads); - sched_left = max_t(unsigned long long, sched_left, 1); - } else { - sched_left = 0; - } - t = tsk; - do { - if (unlikely(t->flags & PF_EXITING)) - continue; - - ticks = cputime_add(cputime_add(t->utime, t->stime), - prof_left); - if (!cputime_eq(prof_expires, cputime_zero) && - (cputime_eq(t->it_prof_expires, cputime_zero) || - cputime_gt(t->it_prof_expires, ticks))) { - t->it_prof_expires = ticks; - } - - ticks = cputime_add(t->utime, virt_left); - if (!cputime_eq(virt_expires, cputime_zero) && - (cputime_eq(t->it_virt_expires, cputime_zero) || - cputime_gt(t->it_virt_expires, ticks))) { - t->it_virt_expires = ticks; - } - - sched = t->se.sum_exec_runtime + sched_left; - if (sched_expires && (t->it_sched_expires == 0 || - t->it_sched_expires > sched)) { - t->it_sched_expires = sched; - } - } while ((t = next_thread(t)) != tsk); - } + if (!cputime_eq(prof_expires, cputime_zero) && + (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) || + cputime_gt(sig->cputime_expires.prof_exp, prof_expires))) + sig->cputime_expires.prof_exp = prof_expires; + if (!cputime_eq(virt_expires, cputime_zero) && + (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) || + cputime_gt(sig->cputime_expires.virt_exp, virt_expires))) + sig->cputime_expires.virt_exp = virt_expires; + if (sched_expires != 0 && + (sig->cputime_expires.sched_exp == 0 || + sig->cputime_expires.sched_exp > sched_expires)) + sig->cputime_expires.sched_exp = sched_expires; } /* @@ -1314,6 +1277,78 @@ out: ++timer->it_requeue_pending; } +/** + * task_cputime_zero - Check a task_cputime struct for all zero fields. + * + * @cputime: The struct to compare. + * + * Checks @cputime to see if all fields are zero. Returns true if all fields + * are zero, false if any field is nonzero. + */ +static inline int task_cputime_zero(const struct task_cputime *cputime) +{ + if (cputime_eq(cputime->utime, cputime_zero) && + cputime_eq(cputime->stime, cputime_zero) && + cputime->sum_exec_runtime == 0) + return 1; + return 0; +} + +/** + * task_cputime_expired - Compare two task_cputime entities. + * + * @sample: The task_cputime structure to be checked for expiration. + * @expires: Expiration times, against which @sample will be checked. + * + * Checks @sample against @expires to see if any field of @sample has expired. + * Returns true if any field of the former is greater than the corresponding + * field of the latter if the latter field is set. Otherwise returns false. + */ +static inline int task_cputime_expired(const struct task_cputime *sample, + const struct task_cputime *expires) +{ + if (!cputime_eq(expires->utime, cputime_zero) && + cputime_ge(sample->utime, expires->utime)) + return 1; + if (!cputime_eq(expires->stime, cputime_zero) && + cputime_ge(cputime_add(sample->utime, sample->stime), + expires->stime)) + return 1; + if (expires->sum_exec_runtime != 0 && + sample->sum_exec_runtime >= expires->sum_exec_runtime) + return 1; + return 0; +} + +/** + * fastpath_timer_check - POSIX CPU timers fast path. + * + * @tsk: The task (thread) being checked. + * @sig: The signal pointer for that task. + * + * If there are no timers set return false. Otherwise snapshot the task and + * thread group timers, then compare them with the corresponding expiration + # times. Returns true if a timer has expired, else returns false. + */ +static inline int fastpath_timer_check(struct task_struct *tsk, + struct signal_struct *sig) +{ + struct task_cputime task_sample = { + .utime = tsk->utime, + .stime = tsk->stime, + .sum_exec_runtime = tsk->se.sum_exec_runtime + }; + struct task_cputime group_sample; + + if (task_cputime_zero(&tsk->cputime_expires) && + task_cputime_zero(&sig->cputime_expires)) + return 0; + if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) + return 1; + thread_group_cputime(tsk, &group_sample); + return task_cputime_expired(&group_sample, &sig->cputime_expires); +} + /* * This is called from the timer interrupt handler. The irq handler has * already updated our counts. We need to check if any timers fire now. @@ -1323,30 +1358,29 @@ void run_posix_cpu_timers(struct task_struct *tsk) { LIST_HEAD(firing); struct k_itimer *timer, *next; + struct signal_struct *sig; + struct sighand_struct *sighand; + unsigned long flags; BUG_ON(!irqs_disabled()); -#define UNEXPIRED(clock) \ - (cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \ - cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires)) - - if (UNEXPIRED(prof) && UNEXPIRED(virt) && - (tsk->it_sched_expires == 0 || - tsk->se.sum_exec_runtime < tsk->it_sched_expires)) - return; - -#undef UNEXPIRED - + /* Pick up tsk->signal and make sure it's valid. */ + sig = tsk->signal; /* - * Double-check with locks held. + * The fast path checks that there are no expired thread or thread + * group timers. If that's so, just return. Also check that + * tsk->signal is non-NULL; this probably can't happen but cover the + * possibility anyway. */ - read_lock(&tasklist_lock); - if (likely(tsk->signal != NULL)) { - spin_lock(&tsk->sighand->siglock); - + if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) { + return; + } + sighand = lock_task_sighand(tsk, &flags); + if (likely(sighand)) { /* - * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N] - * all the timers that are firing, and put them on the firing list. + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and + * put them on the firing list. */ check_thread_timers(tsk, &firing); check_process_timers(tsk, &firing); @@ -1359,9 +1393,8 @@ void run_posix_cpu_timers(struct task_struct *tsk) * that gets the timer lock before we do will give it up and * spin until we've taken care of that timer below. */ - spin_unlock(&tsk->sighand->siglock); } - read_unlock(&tasklist_lock); + unlock_task_sighand(tsk, &flags); /* * Now that all the timers on our list have the firing flag, @@ -1389,10 +1422,9 @@ void run_posix_cpu_timers(struct task_struct *tsk) /* * Set one of the process-wide special case CPU timers. - * The tasklist_lock and tsk->sighand->siglock must be held by the caller. - * The oldval argument is null for the RLIMIT_CPU timer, where *newval is - * absolute; non-null for ITIMER_*, where *newval is relative and we update - * it to be absolute, *oldval is absolute and we update it to be relative. + * The tsk->sighand->siglock must be held by the caller. + * The *newval argument is relative and we update it to be absolute, *oldval + * is absolute and we update it to be relative. */ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval) @@ -1435,13 +1467,14 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_ge(list_first_entry(head, struct cpu_timer_list, entry)->expires.cpu, *newval)) { - /* - * Rejigger each thread's expiry time so that one will - * notice before we hit the process-cumulative expiry time. - */ - union cpu_time_count expires = { .sched = 0 }; - expires.cpu = *newval; - process_timer_rebalance(tsk, clock_idx, expires, now); + switch (clock_idx) { + case CPUCLOCK_PROF: + tsk->signal->cputime_expires.prof_exp = *newval; + break; + case CPUCLOCK_VIRT: + tsk->signal->cputime_expires.virt_exp = *newval; + break; + } } } diff --git a/kernel/sched.c b/kernel/sched.c index cc1f81b50b82..c51b5d276665 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4036,6 +4036,25 @@ DEFINE_PER_CPU(struct kernel_stat, kstat); EXPORT_PER_CPU_SYMBOL(kstat); +/* + * Return any ns on the sched_clock that have not yet been banked in + * @p in case that task is currently running. + * + * Called with task_rq_lock() held on @rq. + */ +static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq) +{ + if (task_current(rq, p)) { + u64 delta_exec; + + update_rq_clock(rq); + delta_exec = rq->clock - p->se.exec_start; + if ((s64)delta_exec > 0) + return delta_exec; + } + return 0; +} + /* * Return p->sum_exec_runtime plus any more ns on the sched_clock * that have not yet been banked in case the task is currently running. @@ -4043,17 +4062,31 @@ EXPORT_PER_CPU_SYMBOL(kstat); unsigned long long task_sched_runtime(struct task_struct *p) { unsigned long flags; - u64 ns, delta_exec; + u64 ns; struct rq *rq; rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime; - if (task_current(rq, p)) { - update_rq_clock(rq); - delta_exec = rq->clock - p->se.exec_start; - if ((s64)delta_exec > 0) - ns += delta_exec; - } + ns = p->se.sum_exec_runtime + task_delta_exec(p, rq); + task_rq_unlock(rq, &flags); + + return ns; +} + +/* + * Return sum_exec_runtime for the thread group plus any more ns on the + * sched_clock that have not yet been banked in case the task is currently + * running. + */ +unsigned long long thread_group_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + u64 ns; + struct rq *rq; + struct task_cputime totals; + + rq = task_rq_lock(p, &flags); + thread_group_cputime(p, &totals); + ns = totals.sum_exec_runtime + task_delta_exec(p, rq); task_rq_unlock(rq, &flags); return ns; @@ -4070,6 +4103,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime) cputime64_t tmp; p->utime = cputime_add(p->utime, cputime); + account_group_user_time(p, cputime); /* Add user time to cpustat. */ tmp = cputime_to_cputime64(cputime); @@ -4094,6 +4128,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime) tmp = cputime_to_cputime64(cputime); p->utime = cputime_add(p->utime, cputime); + account_group_user_time(p, cputime); p->gtime = cputime_add(p->gtime, cputime); cpustat->user = cputime64_add(cpustat->user, tmp); @@ -4129,6 +4164,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset, } p->stime = cputime_add(p->stime, cputime); + account_group_system_time(p, cputime); /* Add system time to cpustat. */ tmp = cputime_to_cputime64(cputime); @@ -4170,6 +4206,7 @@ void account_steal_time(struct task_struct *p, cputime_t steal) if (p == rq->idle) { p->stime = cputime_add(p->stime, steal); + account_group_system_time(p, steal); if (atomic_read(&rq->nr_iowait) > 0) cpustat->iowait = cputime64_add(cpustat->iowait, tmp); else diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index fb8994c6d4bb..99aa31acc544 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -507,6 +507,7 @@ static void update_curr(struct cfs_rq *cfs_rq) struct task_struct *curtask = task_of(curr); cpuacct_charge(curtask, delta_exec); + account_group_exec_runtime(curtask, delta_exec); } } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 552310798dad..8375e69af36a 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -483,6 +483,8 @@ static void update_curr_rt(struct rq *rq) schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + curr->se.exec_start = rq->clock; cpuacct_charge(curr, delta_exec); @@ -1412,7 +1414,7 @@ static void watchdog(struct rq *rq, struct task_struct *p) p->rt.timeout++; next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); if (p->rt.timeout > next) - p->it_sched_expires = p->se.sum_exec_runtime; + p->cputime_expires.sched_exp = p->se.sum_exec_runtime; } } diff --git a/kernel/signal.c b/kernel/signal.c index e661b01d340f..6eea5826d618 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1338,6 +1338,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) struct siginfo info; unsigned long flags; struct sighand_struct *psig; + struct task_cputime cputime; int ret = sig; BUG_ON(sig == -1); @@ -1368,10 +1369,9 @@ int do_notify_parent(struct task_struct *tsk, int sig) info.si_uid = tsk->uid; - info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime, - tsk->signal->utime)); - info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime, - tsk->signal->stime)); + thread_group_cputime(tsk, &cputime); + info.si_utime = cputime_to_jiffies(cputime.utime); + info.si_stime = cputime_to_jiffies(cputime.stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) diff --git a/kernel/sys.c b/kernel/sys.c index 038a7bc0901d..d046a7a055c2 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -853,38 +853,28 @@ asmlinkage long sys_setfsgid(gid_t gid) return old_fsgid; } +void do_sys_times(struct tms *tms) +{ + struct task_cputime cputime; + cputime_t cutime, cstime; + + spin_lock_irq(¤t->sighand->siglock); + thread_group_cputime(current, &cputime); + cutime = current->signal->cutime; + cstime = current->signal->cstime; + spin_unlock_irq(¤t->sighand->siglock); + tms->tms_utime = cputime_to_clock_t(cputime.utime); + tms->tms_stime = cputime_to_clock_t(cputime.stime); + tms->tms_cutime = cputime_to_clock_t(cutime); + tms->tms_cstime = cputime_to_clock_t(cstime); +} + asmlinkage long sys_times(struct tms __user * tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { struct tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - spin_lock_irq(&tsk->sighand->siglock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - - tmp.tms_utime = cputime_to_clock_t(utime); - tmp.tms_stime = cputime_to_clock_t(stime); - tmp.tms_cutime = cputime_to_clock_t(cutime); - tmp.tms_cstime = cputime_to_clock_t(cstime); + + do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } @@ -1445,7 +1435,6 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) { struct rlimit new_rlim, *old_rlim; - unsigned long it_prof_secs; int retval; if (resource >= RLIM_NLIMITS) @@ -1491,18 +1480,7 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) if (new_rlim.rlim_cur == RLIM_INFINITY) goto out; - it_prof_secs = cputime_to_secs(current->signal->it_prof_expires); - if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) { - unsigned long rlim_cur = new_rlim.rlim_cur; - cputime_t cputime; - - cputime = secs_to_cputime(rlim_cur); - read_lock(&tasklist_lock); - spin_lock_irq(¤t->sighand->siglock); - set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); - spin_unlock_irq(¤t->sighand->siglock); - read_unlock(&tasklist_lock); - } + update_rlimit_cpu(new_rlim.rlim_cur); out: return 0; } @@ -1540,11 +1518,8 @@ out: * */ -static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r, - cputime_t *utimep, cputime_t *stimep) +static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) { - *utimep = cputime_add(*utimep, t->utime); - *stimep = cputime_add(*stimep, t->stime); r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; @@ -1558,12 +1533,13 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; cputime_t utime, stime; + struct task_cputime cputime; memset((char *) r, 0, sizeof *r); utime = stime = cputime_zero; if (who == RUSAGE_THREAD) { - accumulate_thread_rusage(p, r, &utime, &stime); + accumulate_thread_rusage(p, r); goto out; } @@ -1586,8 +1562,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) break; case RUSAGE_SELF: - utime = cputime_add(utime, p->signal->utime); - stime = cputime_add(stime, p->signal->stime); + thread_group_cputime(p, &cputime); + utime = cputime_add(utime, cputime.utime); + stime = cputime_add(stime, cputime.stime); r->ru_nvcsw += p->signal->nvcsw; r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; @@ -1596,7 +1573,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_oublock += p->signal->oublock; t = p; do { - accumulate_thread_rusage(t, r, &utime, &stime); + accumulate_thread_rusage(t, r); t = next_thread(t); } while (t != p); break; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 03fc6a81ae32..69649783c266 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -75,6 +75,7 @@ #include #include #include +#include #include "avc.h" #include "objsec.h" @@ -2321,13 +2322,7 @@ static void selinux_bprm_post_apply_creds(struct linux_binprm *bprm) initrlim = init_task.signal->rlim+i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } - if (current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * This will cause RLIMIT_CPU calculations - * to be refigured. - */ - current->it_prof_expires = jiffies_to_cputime(1); - } + update_rlimit_cpu(rlim->rlim_cur); } /* Wake up the parent if it is waiting so that it can -- cgit v1.2.3 From 15afe09bf496ae10c989e1a375a6b5da7bd3e16e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sat, 20 Sep 2008 23:38:02 +0200 Subject: sched: wakeup preempt when small overlap Lin Ming reported a 10% OLTP regression against 2.6.27-rc4. The difference seems to come from different preemption agressiveness, which affects the cache footprint of the workload and its effective cache trashing. Aggresively preempt a task if its avg overlap is very small, this should avoid the task going to sleep and find it still running when we schedule back to it - saving a wakeup. Reported-by: Lin Ming Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 +- kernel/sched.c | 12 ++++++------ kernel/sched_fair.c | 13 ++++++++++--- kernel/sched_features.h | 1 + kernel/sched_idletask.c | 6 +++--- kernel/sched_rt.c | 2 +- 6 files changed, 22 insertions(+), 14 deletions(-) (limited to 'kernel/sched_rt.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index b3b7a8f32477..d8e699b55858 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -897,7 +897,7 @@ struct sched_class { void (*yield_task) (struct rq *rq); int (*select_task_rq)(struct task_struct *p, int sync); - void (*check_preempt_curr) (struct rq *rq, struct task_struct *p); + void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync); struct task_struct * (*pick_next_task) (struct rq *rq); void (*put_prev_task) (struct rq *rq, struct task_struct *p); diff --git a/kernel/sched.c b/kernel/sched.c index 0d8905a1b8ca..ad9d39b021f8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -604,9 +604,9 @@ struct rq { static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -static inline void check_preempt_curr(struct rq *rq, struct task_struct *p) +static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync) { - rq->curr->sched_class->check_preempt_curr(rq, p); + rq->curr->sched_class->check_preempt_curr(rq, p, sync); } static inline int cpu_of(struct rq *rq) @@ -2282,7 +2282,7 @@ out_running: trace_mark(kernel_sched_wakeup, "pid %d state %ld ## rq %p task %p rq->curr %p", p->pid, p->state, rq, p, rq->curr); - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, sync); p->state = TASK_RUNNING; #ifdef CONFIG_SMP @@ -2417,7 +2417,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) trace_mark(kernel_sched_wakeup_new, "pid %d state %ld ## rq %p task %p rq->curr %p", p->pid, p->state, rq, p, rq->curr); - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) p->sched_class->task_wake_up(rq, p); @@ -2877,7 +2877,7 @@ static void pull_task(struct rq *src_rq, struct task_struct *p, * Note that idle threads have a prio of MAX_PRIO, for this test * to be always true for them. */ - check_preempt_curr(this_rq, p); + check_preempt_curr(this_rq, p, 0); } /* @@ -6007,7 +6007,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) set_task_cpu(p, dest_cpu); if (on_rq) { activate_task(rq_dest, p, 0); - check_preempt_curr(rq_dest, p); + check_preempt_curr(rq_dest, p, 0); } done: ret = 1; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a10ac0bcee64..7328383690f1 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1331,7 +1331,7 @@ static inline int depth_se(struct sched_entity *se) /* * Preempt the current task with a newly woken task if needed: */ -static void check_preempt_wakeup(struct rq *rq, struct task_struct *p) +static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) { struct task_struct *curr = rq->curr; struct cfs_rq *cfs_rq = task_cfs_rq(curr); @@ -1367,6 +1367,13 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p) if (!sched_feat(WAKEUP_PREEMPT)) return; + if (sched_feat(WAKEUP_OVERLAP) && sync && + se->avg_overlap < sysctl_sched_migration_cost && + pse->avg_overlap < sysctl_sched_migration_cost) { + resched_task(curr); + return; + } + /* * preemption test can be made between sibling entities who are in the * same cfs_rq i.e who have a common parent. Walk up the hierarchy of @@ -1649,7 +1656,7 @@ static void prio_changed_fair(struct rq *rq, struct task_struct *p, if (p->prio > oldprio) resched_task(rq->curr); } else - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); } /* @@ -1666,7 +1673,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p, if (running) resched_task(rq->curr); else - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); } /* Account for a task changing its policy or group. diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 9353ca78154e..bf027a7accf8 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -11,3 +11,4 @@ SCHED_FEAT(ASYM_GRAN, 1) SCHED_FEAT(LB_BIAS, 1) SCHED_FEAT(LB_WAKEUP_UPDATE, 1) SCHED_FEAT(ASYM_EFF_LOAD, 1) +SCHED_FEAT(WAKEUP_OVERLAP, 1) diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index 3a4f92dbbe66..dec4ccabe2f5 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -14,7 +14,7 @@ static int select_task_rq_idle(struct task_struct *p, int sync) /* * Idle tasks are unconditionally rescheduled: */ -static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p) +static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sync) { resched_task(rq->idle); } @@ -76,7 +76,7 @@ static void switched_to_idle(struct rq *rq, struct task_struct *p, if (running) resched_task(rq->curr); else - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); } static void prio_changed_idle(struct rq *rq, struct task_struct *p, @@ -93,7 +93,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p, if (p->prio > oldprio) resched_task(rq->curr); } else - check_preempt_curr(rq, p); + check_preempt_curr(rq, p, 0); } /* diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 552310798dad..6d2d0a5d030b 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -783,7 +783,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) /* * Preempt the current task with a newly woken task if needed: */ -static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p) +static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int sync) { if (p->prio < rq->curr->prio) { resched_task(rq->curr); -- cgit v1.2.3 From 78333cdd0e472180743d35988e576d6ecc6f6ddb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 23 Sep 2008 15:33:43 +0200 Subject: sched: add some comments to the bandwidth code Hopefully clarify some of this code a little. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'kernel/sched_rt.c') diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 2e228bd5395e..d570a8cc4fcd 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -231,6 +231,9 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_SMP +/* + * We ran out of runtime, see if we can borrow some from our neighbours. + */ static int do_balance_runtime(struct rt_rq *rt_rq) { struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); @@ -250,9 +253,18 @@ static int do_balance_runtime(struct rt_rq *rt_rq) continue; spin_lock(&iter->rt_runtime_lock); + /* + * Either all rqs have inf runtime and there's nothing to steal + * or __disable_runtime() below sets a specific rq to inf to + * indicate its been disabled and disalow stealing. + */ if (iter->rt_runtime == RUNTIME_INF) goto next; + /* + * From runqueues with spare time, take 1/n part of their + * spare time, but no more than our period. + */ diff = iter->rt_runtime - iter->rt_time; if (diff > 0) { diff = div_u64((u64)diff, weight); @@ -274,6 +286,9 @@ next: return more; } +/* + * Ensure this RQ takes back all the runtime it lend to its neighbours. + */ static void __disable_runtime(struct rq *rq) { struct root_domain *rd = rq->rd; @@ -289,17 +304,33 @@ static void __disable_runtime(struct rq *rq) spin_lock(&rt_b->rt_runtime_lock); spin_lock(&rt_rq->rt_runtime_lock); + /* + * Either we're all inf and nobody needs to borrow, or we're + * already disabled and thus have nothing to do, or we have + * exactly the right amount of runtime to take out. + */ if (rt_rq->rt_runtime == RUNTIME_INF || rt_rq->rt_runtime == rt_b->rt_runtime) goto balanced; spin_unlock(&rt_rq->rt_runtime_lock); + /* + * Calculate the difference between what we started out with + * and what we current have, that's the amount of runtime + * we lend and now have to reclaim. + */ want = rt_b->rt_runtime - rt_rq->rt_runtime; + /* + * Greedy reclaim, take back as much as we can. + */ for_each_cpu_mask(i, rd->span) { struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); s64 diff; + /* + * Can't reclaim from ourselves or disabled runqueues. + */ if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF) continue; @@ -319,8 +350,16 @@ static void __disable_runtime(struct rq *rq) } spin_lock(&rt_rq->rt_runtime_lock); + /* + * We cannot be left wanting - that would mean some runtime + * leaked out of the system. + */ BUG_ON(want); balanced: + /* + * Disable all the borrow logic by pretending we have inf + * runtime - in which case borrowing doesn't make sense. + */ rt_rq->rt_runtime = RUNTIME_INF; spin_unlock(&rt_rq->rt_runtime_lock); spin_unlock(&rt_b->rt_runtime_lock); @@ -343,6 +382,9 @@ static void __enable_runtime(struct rq *rq) if (unlikely(!scheduler_running)) return; + /* + * Reset each runqueue's bandwidth settings + */ for_each_leaf_rt_rq(rt_rq, rq) { struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); -- cgit v1.2.3 From f6121f4f8708195e88cbdf8dd8d171b226b3f858 Mon Sep 17 00:00:00 2001 From: Dario Faggioli Date: Fri, 3 Oct 2008 17:40:46 +0200 Subject: sched_rt.c: resch needed in rt_rq_enqueue() for the root rt_rq While working on the new version of the code for SCHED_SPORADIC I noticed something strange in the present throttling mechanism. More specifically in the throttling timer handler in sched_rt.c (do_sched_rt_period_timer()) and in rt_rq_enqueue(). The problem is that, when unthrottling a runqueue, rt_rq_enqueue() only asks for rescheduling if the runqueue has a sched_entity associated to it (i.e., rt_rq->rt_se != NULL). Now, if the runqueue is the root rq (which has a rt_se = NULL) rescheduling does not take place, and it is delayed to some undefined instant in the future. This imply some random bandwidth usage by the RT tasks under throttling. For instance, setting rt_runtime_us/rt_period_us = 950ms/1000ms an RT task will get less than 95%. In our tests we got something varying between 70% to 95%. Using smaller time values, e.g., 95ms/100ms, things are even worse, and I can see values also going down to 20-25%!! The tests we performed are simply running 'yes' as a SCHED_FIFO task, and checking the CPU usage with top, but we can investigate thoroughly if you think it is needed. Things go much better, for us, with the attached patch... Don't know if it is the best approach, but it solved the issue for us. Signed-off-by: Dario Faggioli Signed-off-by: Michael Trimarchi Acked-by: Peter Zijlstra Cc: Signed-off-by: Ingo Molnar --- kernel/sched_rt.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/sched_rt.c') diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index d570a8cc4fcd..cdf5740ab03e 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -102,12 +102,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { + struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; struct sched_rt_entity *rt_se = rt_rq->rt_se; - if (rt_se && !on_rt_rq(rt_se) && rt_rq->rt_nr_running) { - struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr; - - enqueue_rt_entity(rt_se); + if (rt_rq->rt_nr_running) { + if (rt_se && !on_rt_rq(rt_se)) + enqueue_rt_entity(rt_se); if (rt_rq->highest_prio < curr->prio) resched_task(curr); } -- cgit v1.2.3