From e9f238c3041e2582a710e75910c8cbf2a98e51b2 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 11 Aug 2012 12:38:26 -0700 Subject: procfs: Print task uids and gids in the userns that opened the proc file Instead of using current_userns() use the userns of the opener of the file so that if the file is passed between processes the contents of the file do not change. Acked-by: Serge E. Hallyn Signed-off-by: "Eric W. Biederman" --- fs/proc/array.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index c1c207c36cae..554434265613 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -162,7 +162,7 @@ static inline const char *get_task_state(struct task_struct *tsk) static inline void task_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *p) { - struct user_namespace *user_ns = current_user_ns(); + struct user_namespace *user_ns = seq_user_ns(m); struct group_info *group_info; int g; struct fdtable *fdt = NULL; -- cgit v1.2.3 From e80d0a1ae8bb8fee0edd37427836f108b30f596b Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 21 Nov 2012 16:26:44 +0100 Subject: cputime: Rename thread_group_times to thread_group_cputime_adjusted We have thread_group_cputime() and thread_group_times(). The naming doesn't provide enough information about the difference between these two APIs. To lower the confusion, rename thread_group_times() to thread_group_cputime_adjusted(). This name better suggests that it's a version of thread_group_cputime() that does some stabilization on the raw cputime values. ie here: scale on top of CFS runtime stats and bound lower value for monotonicity. Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Steven Rostedt Cc: Paul Gortmaker --- fs/proc/array.c | 4 ++-- include/linux/sched.h | 4 ++-- kernel/exit.c | 4 ++-- kernel/sched/cputime.c | 8 ++++---- kernel/sys.c | 6 +++--- 5 files changed, 13 insertions(+), 13 deletions(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index c1c207c36cae..d3696708fc1a 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -438,7 +438,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, min_flt += sig->min_flt; maj_flt += sig->maj_flt; - thread_group_times(task, &utime, &stime); + thread_group_cputime_adjusted(task, &utime, &stime); gtime += sig->gtime; } @@ -454,7 +454,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (!whole) { min_flt = task->min_flt; maj_flt = task->maj_flt; - task_times(task, &utime, &stime); + task_cputime_adjusted(task, &utime, &stime); gtime = task->gtime; } diff --git a/include/linux/sched.h b/include/linux/sched.h index e1581a029e3d..e75cab5820ab 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1751,8 +1751,8 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } -extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st); -extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st); +extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); +extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); /* * Per process flags diff --git a/kernel/exit.c b/kernel/exit.c index 346616c0092c..618f7ee56003 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1186,11 +1186,11 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) * as other threads in the parent group can be right * here reaping other children at the same time. * - * We use thread_group_times() to get times for the thread + * We use thread_group_cputime_adjusted() to get times for the thread * group, which consolidates times for all threads in the * group including the group leader. */ - thread_group_times(p, &tgutime, &tgstime); + thread_group_cputime_adjusted(p, &tgutime, &tgstime); spin_lock_irq(&p->real_parent->sighand->siglock); psig = p->real_parent->signal; sig = p->signal; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index e56f138a23c7..7dc155371b95 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -445,13 +445,13 @@ void account_idle_ticks(unsigned long ticks) * Use precise platform statistics if available: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING -void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { *ut = p->utime; *st = p->stime; } -void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { struct task_cputime cputime; @@ -516,7 +516,7 @@ static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) return (__force cputime_t) temp; } -void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { cputime_t rtime, utime = p->utime, total = utime + p->stime; @@ -543,7 +543,7 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) /* * Must be called with siglock held. */ -void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { struct signal_struct *sig = p->signal; struct task_cputime cputime; diff --git a/kernel/sys.c b/kernel/sys.c index e6e0ece5f6a0..265b37690421 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1046,7 +1046,7 @@ void do_sys_times(struct tms *tms) cputime_t tgutime, tgstime, cutime, cstime; spin_lock_irq(¤t->sighand->siglock); - thread_group_times(current, &tgutime, &tgstime); + thread_group_cputime_adjusted(current, &tgutime, &tgstime); cutime = current->signal->cutime; cstime = current->signal->cstime; spin_unlock_irq(¤t->sighand->siglock); @@ -1704,7 +1704,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) utime = stime = 0; if (who == RUSAGE_THREAD) { - task_times(current, &utime, &stime); + task_cputime_adjusted(current, &utime, &stime); accumulate_thread_rusage(p, r); maxrss = p->signal->maxrss; goto out; @@ -1730,7 +1730,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) break; case RUSAGE_SELF: - thread_group_times(p, &tgutime, &tgstime); + thread_group_cputime_adjusted(p, &tgutime, &tgstime); utime += tgutime; stime += tgstime; r->ru_nvcsw += p->signal->nvcsw; -- cgit v1.2.3 From 7b9a7ec565505699f503b4fcf61500dceb36e744 Mon Sep 17 00:00:00 2001 From: Andrew Vagin Date: Mon, 17 Dec 2012 16:03:10 -0800 Subject: proc: don't show nonexistent capabilities Without this patch it is really hard to interpret a bounding set, if CAP_LAST_CAP is unknown for a current kernel. Non-existant capabilities can not be deleted from a bounding set with help of prctl. E.g.: Here are two examples without/with this patch. CapBnd: ffffffe0fdecffff CapBnd: 00000000fdecffff I suggest to hide non-existent capabilities. Here is two reasons. * It's logically and easier for using. * It helps to checkpoint-restore capabilities of tasks, because tasks can be restored on another kernel, where CAP_LAST_CAP is bigger. Signed-off-by: Andrew Vagin Cc: Andrew G. Morgan Reviewed-by: Serge E. Hallyn Cc: Pavel Emelyanov Reviewed-by: Kees Cook Cc: KAMEZAWA Hiroyuki Cc: James Morris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index d3696708fc1a..377a37366dde 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -308,6 +308,10 @@ static void render_cap_t(struct seq_file *m, const char *header, seq_putc(m, '\n'); } +/* Remove non-existent capabilities */ +#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \ + CAP_TO_MASK(CAP_LAST_CAP + 1) - 1) + static inline void task_cap(struct seq_file *m, struct task_struct *p) { const struct cred *cred; @@ -321,6 +325,11 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p) cap_bset = cred->cap_bset; rcu_read_unlock(); + NORM_CAPS(cap_inheritable); + NORM_CAPS(cap_permitted); + NORM_CAPS(cap_effective); + NORM_CAPS(cap_bset); + render_cap_t(m, "CapInh:\t", &cap_inheritable); render_cap_t(m, "CapPrm:\t", &cap_permitted); render_cap_t(m, "CapEff:\t", &cap_effective); -- cgit v1.2.3 From 2f4b3bf6b2318cfaa177ec5a802f4d8d6afbd816 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 17 Dec 2012 16:03:14 -0800 Subject: /proc/pid/status: add "Seccomp" field It is currently impossible to examine the state of seccomp for a given process. While attaching with gdb and attempting "call prctl(PR_GET_SECCOMP,...)" will work with some situations, it is not reliable. If the process is in seccomp mode 1, this query will kill the process (prctl not allowed), if the process is in mode 2 with prctl not allowed, it will similarly be killed, and in weird cases, if prctl is filtered to return errno 0, it can look like seccomp is disabled. When reviewing the state of running processes, there should be a way to externally examine the seccomp mode. ("Did this build of Chrome end up using seccomp?" "Did my distro ship ssh with seccomp enabled?") This adds the "Seccomp" line to /proc/$pid/status. Signed-off-by: Kees Cook Reviewed-by: Cyrill Gorcunov Cc: Andrea Arcangeli Cc: James Morris Acked-by: Serge E. Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.txt | 2 ++ fs/proc/array.c | 8 ++++++++ 2 files changed, 10 insertions(+) (limited to 'fs/proc/array.c') diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 74cb394e6888..12665ee7094a 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -181,6 +181,7 @@ read the file /proc/PID/status: CapPrm: 0000000000000000 CapEff: 0000000000000000 CapBnd: ffffffffffffffff + Seccomp: 0 voluntary_ctxt_switches: 0 nonvoluntary_ctxt_switches: 1 @@ -237,6 +238,7 @@ Table 1-2: Contents of the status files (as of 2.6.30-rc7) CapPrm bitmap of permitted capabilities CapEff bitmap of effective capabilities CapBnd bitmap of capabilities bounding set + Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...) Cpus_allowed mask of CPUs on which this process may run Cpus_allowed_list Same as previous, but in "list format" Mems_allowed mask of memory nodes allowed to this process diff --git a/fs/proc/array.c b/fs/proc/array.c index 377a37366dde..077235ffb38b 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -336,6 +336,13 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p) render_cap_t(m, "CapBnd:\t", &cap_bset); } +static inline void task_seccomp(struct seq_file *m, struct task_struct *p) +{ +#ifdef CONFIG_SECCOMP + seq_printf(m, "Seccomp:\t%d\n", p->seccomp.mode); +#endif +} + static inline void task_context_switch_counts(struct seq_file *m, struct task_struct *p) { @@ -369,6 +376,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, } task_sig(m, task); task_cap(m, task); + task_seccomp(m, task); task_cpus_allowed(m, task); cpuset_task_status_allowed(m, task); task_context_switch_counts(m, task); -- cgit v1.2.3 From 8d238027b87e654be552eabdf492042a34c5c300 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 17 Dec 2012 16:03:17 -0800 Subject: proc: pid/status: show all supplementary groups We display a list of supplementary group for each process in /proc//status. However, we show only the first 32 groups, not all of them. Although this is rare, but sometimes processes do have more than 32 supplementary groups, and this kernel limitation breaks user-space apps that rely on the group list in /proc//status. Number 32 comes from the internal NGROUPS_SMALL macro which defines the length for the internal kernel "small" groups buffer. There is no apparent reason to limit to this value. This patch removes the 32 groups printing limit. The Linux kernel limits the amount of supplementary groups by NGROUPS_MAX, which is currently set to 65536. And this is the maximum count of groups we may possibly print. Signed-off-by: Artem Bityutskiy Acked-by: Serge E. Hallyn Acked-by: Kees Cook Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/proc/array.c') diff --git a/fs/proc/array.c b/fs/proc/array.c index 077235ffb38b..439544fec388 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -212,7 +212,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, group_info = cred->group_info; task_unlock(p); - for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++) + for (g = 0; g < group_info->ngroups; g++) seq_printf(m, "%d ", from_kgid_munged(user_ns, GROUP_AT(group_info, g))); put_cred(cred); -- cgit v1.2.3 From 138d22b58696c506799f8de759804083ff9effae Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Mon, 17 Dec 2012 16:05:02 -0800 Subject: fs, epoll: add procfs fdinfo helper This allows us to print out eventpoll target file descriptor, events and data, the /proc/pid/fdinfo/fd consists of | pos: 0 | flags: 02 | tfd: 5 events: 1d data: ffffffffffffffff enabled: 1 [avagin@: fix for unitialized ret variable] Signed-off-by: Cyrill Gorcunov Acked-by: Pavel Emelyanov Cc: Oleg Nesterov Cc: Andrey Vagin Cc: Al Viro Cc: Alexey Dobriyan Cc: James Bottomley Cc: "Aneesh Kumar K.V" Cc: Alexey Dobriyan Cc: Matthew Helsley Cc: "J. Bruce Fields" Cc: "Aneesh Kumar K.V" Cc: Tvrtko Ursulin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 28 ++++++++++++++++++++++++++++ fs/proc/array.c | 2 +- fs/signalfd.c | 18 ++++++++++++++++++ include/linux/proc_fs.h | 3 +++ 4 files changed, 50 insertions(+), 1 deletion(-) (limited to 'fs/proc/array.c') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index cd96649bfe62..be56b21435f8 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -38,6 +38,8 @@ #include #include #include +#include +#include /* * LOCKING: @@ -783,8 +785,34 @@ static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait) return pollflags != -1 ? pollflags : 0; } +#ifdef CONFIG_PROC_FS +static int ep_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct eventpoll *ep = f->private_data; + struct rb_node *rbp; + int ret = 0; + + mutex_lock(&ep->mtx); + for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + struct epitem *epi = rb_entry(rbp, struct epitem, rbn); + + ret = seq_printf(m, "tfd: %8d events: %8x data: %16llx\n", + epi->ffd.fd, epi->event.events, + (long long)epi->event.data); + if (ret) + break; + } + mutex_unlock(&ep->mtx); + + return ret; +} +#endif + /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = ep_show_fdinfo, +#endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, diff --git a/fs/proc/array.c b/fs/proc/array.c index 439544fec388..060a56a91278 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -220,7 +220,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, seq_putc(m, '\n'); } -static void render_sigset_t(struct seq_file *m, const char *header, +void render_sigset_t(struct seq_file *m, const char *header, sigset_t *set) { int i; diff --git a/fs/signalfd.c b/fs/signalfd.c index 8bee4e570911..b53486961735 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -29,6 +29,7 @@ #include #include #include +#include void signalfd_cleanup(struct sighand_struct *sighand) { @@ -227,7 +228,24 @@ static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count, return total ? total: ret; } +#ifdef CONFIG_PROC_FS +static int signalfd_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct signalfd_ctx *ctx = f->private_data; + sigset_t sigmask; + + sigmask = ctx->sigmask; + signotset(&sigmask); + render_sigset_t(m, "sigmask:\t", &sigmask); + + return 0; +} +#endif + static const struct file_operations signalfd_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = signalfd_show_fdinfo, +#endif .release = signalfd_release, .poll = signalfd_poll, .read = signalfd_read, diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 3fd2e871ff1b..b4f70f0a9a48 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -290,4 +290,7 @@ static inline struct net *PDE_NET(struct proc_dir_entry *pde) return pde->parent->data; } +#include + +void render_sigset_t(struct seq_file *m, const char *header, sigset_t *set); #endif /* _LINUX_PROC_FS_H */ -- cgit v1.2.3 From 6fac4829ce0ef9b7f24369086ce5f0e9f38d37bc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 13 Nov 2012 14:20:55 +0100 Subject: cputime: Use accessors to read task cputime stats This is in preparation for the full dynticks feature. While remotely reading the cputime of a task running in a full dynticks CPU, we'll need to do some extra-computation. This way we can account the time it spent tickless in userspace since its last cputime snapshot. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Ingo Molnar Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- arch/alpha/kernel/osf_sys.c | 6 ++++-- arch/x86/kernel/apm_32.c | 11 ++++++----- drivers/isdn/mISDN/stack.c | 7 ++++++- fs/binfmt_elf.c | 8 ++++++-- fs/binfmt_elf_fdpic.c | 7 +++++-- fs/proc/array.c | 4 ++-- include/linux/sched.h | 23 +++++++++++++++++++++++ include/linux/tsacct_kern.h | 3 +++ kernel/acct.c | 6 ++++-- kernel/cpu.c | 4 +++- kernel/delayacct.c | 7 +++++-- kernel/exit.c | 10 ++++++---- kernel/posix-cpu-timers.c | 28 ++++++++++++++++++++++------ kernel/sched/cputime.c | 13 +++++++------ kernel/signal.c | 12 ++++++++---- kernel/tsacct.c | 44 ++++++++++++++++++++++++++++++++++---------- 16 files changed, 144 insertions(+), 49 deletions(-) (limited to 'fs/proc/array.c') diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 14db93e4c8a8..dbc1760f418b 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1139,6 +1139,7 @@ struct rusage32 { SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) { struct rusage32 r; + cputime_t utime, stime; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN) return -EINVAL; @@ -1146,8 +1147,9 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) memset(&r, 0, sizeof(r)); switch (who) { case RUSAGE_SELF: - jiffies_to_timeval32(current->utime, &r.ru_utime); - jiffies_to_timeval32(current->stime, &r.ru_stime); + task_cputime(current, &utime, &stime); + jiffies_to_timeval32(utime, &r.ru_utime); + jiffies_to_timeval32(stime, &r.ru_stime); r.ru_minflt = current->min_flt; r.ru_majflt = current->maj_flt; break; diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index d65464e43503..8d7012b7f402 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -899,6 +899,7 @@ static void apm_cpu_idle(void) static int use_apm_idle; /* = 0 */ static unsigned int last_jiffies; /* = 0 */ static unsigned int last_stime; /* = 0 */ + cputime_t stime; int apm_idle_done = 0; unsigned int jiffies_since_last_check = jiffies - last_jiffies; @@ -906,23 +907,23 @@ static void apm_cpu_idle(void) WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012"); recalc: + task_cputime(current, NULL, &stime); if (jiffies_since_last_check > IDLE_CALC_LIMIT) { use_apm_idle = 0; - last_jiffies = jiffies; - last_stime = current->stime; } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = current->stime - last_stime; + idle_percentage = stime - last_stime; idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); if (apm_info.forbid_idle) use_apm_idle = 0; - last_jiffies = jiffies; - last_stime = current->stime; } + last_jiffies = jiffies; + last_stime = stime; + bucket = IDLE_LEAKY_MAX; while (!need_resched()) { diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c index 5f21f629b7ae..deda591f70b9 100644 --- a/drivers/isdn/mISDN/stack.c +++ b/drivers/isdn/mISDN/stack.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "core.h" static u_int *debug; @@ -202,6 +203,9 @@ static int mISDNStackd(void *data) { struct mISDNstack *st = data; +#ifdef MISDN_MSG_STATS + cputime_t utime, stime; +#endif int err = 0; sigfillset(¤t->blocked); @@ -303,9 +307,10 @@ mISDNStackd(void *data) "msg %d sleep %d stopped\n", dev_name(&st->dev->dev), st->msg_cnt, st->sleep_cnt, st->stopped_cnt); + task_cputime(st->thread, &utime, &stime); printk(KERN_DEBUG "mISDNStackd daemon for %s utime(%ld) stime(%ld)\n", - dev_name(&st->dev->dev), st->thread->utime, st->thread->stime); + dev_name(&st->dev->dev), utime, stime); printk(KERN_DEBUG "mISDNStackd daemon for %s nvcsw(%ld) nivcsw(%ld)\n", dev_name(&st->dev->dev), st->thread->nvcsw, st->thread->nivcsw); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 0c42cdbabecf..49d0b43458b7 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -1320,8 +1321,11 @@ static void fill_prstatus(struct elf_prstatus *prstatus, 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); + cputime_t utime, stime; + + task_cputime(p, &utime, &stime); + cputime_to_timeval(utime, &prstatus->pr_utime); + cputime_to_timeval(stime, &prstatus->pr_stime); } cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime); cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index dc84732e554f..cb240dd3b402 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1375,8 +1375,11 @@ static void fill_prstatus(struct elf_prstatus *prstatus, 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); + cputime_t utime, stime; + + task_cputime(p, &utime, &stime); + cputime_to_timeval(utime, &prstatus->pr_utime); + cputime_to_timeval(stime, &prstatus->pr_stime); } cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime); cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime); diff --git a/fs/proc/array.c b/fs/proc/array.c index 6a91e6ffbcbd..f7ed9ee46eb9 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -449,7 +449,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, do { min_flt += t->min_flt; maj_flt += t->maj_flt; - gtime += t->gtime; + gtime += task_gtime(t); t = next_thread(t); } while (t != task); @@ -472,7 +472,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, min_flt = task->min_flt; maj_flt = task->maj_flt; task_cputime_adjusted(task, &utime, &stime); - gtime = task->gtime; + gtime = task_gtime(task); } /* scale priority and nice values from timeslices to -20..20 */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 6fc8f45de4e9..a9c608b6154e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1792,6 +1792,29 @@ static inline void put_task_struct(struct task_struct *t) __put_task_struct(t); } +static inline cputime_t task_gtime(struct task_struct *t) +{ + return t->gtime; +} + +static inline void task_cputime(struct task_struct *t, + cputime_t *utime, cputime_t *stime) +{ + if (utime) + *utime = t->utime; + if (stime) + *stime = t->stime; +} + +static inline void task_cputime_scaled(struct task_struct *t, + cputime_t *utimescaled, + cputime_t *stimescaled) +{ + if (utimescaled) + *utimescaled = t->utimescaled; + if (stimescaled) + *stimescaled = t->stimescaled; +} extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st); diff --git a/include/linux/tsacct_kern.h b/include/linux/tsacct_kern.h index 44893e5ec8f7..3251965bf4cc 100644 --- a/include/linux/tsacct_kern.h +++ b/include/linux/tsacct_kern.h @@ -23,12 +23,15 @@ static inline void bacct_add_tsk(struct user_namespace *user_ns, #ifdef CONFIG_TASK_XACCT extern void xacct_add_tsk(struct taskstats *stats, struct task_struct *p); extern void acct_update_integrals(struct task_struct *tsk); +extern void acct_account_cputime(struct task_struct *tsk); extern void acct_clear_integrals(struct task_struct *tsk); #else static inline void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) {} static inline void acct_update_integrals(struct task_struct *tsk) {} +static inline void acct_account_cputime(struct task_struct *tsk) +{} static inline void acct_clear_integrals(struct task_struct *tsk) {} #endif /* CONFIG_TASK_XACCT */ diff --git a/kernel/acct.c b/kernel/acct.c index 051e071a06e7..e8b1627ab9c7 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -566,6 +566,7 @@ out: void acct_collect(long exitcode, int group_dead) { struct pacct_struct *pacct = ¤t->signal->pacct; + cputime_t utime, stime; unsigned long vsize = 0; if (group_dead && current->mm) { @@ -593,8 +594,9 @@ void acct_collect(long exitcode, int group_dead) pacct->ac_flag |= ACORE; if (current->flags & PF_SIGNALED) pacct->ac_flag |= AXSIG; - pacct->ac_utime += current->utime; - pacct->ac_stime += current->stime; + task_cputime(current, &utime, &stime); + pacct->ac_utime += utime; + pacct->ac_stime += stime; pacct->ac_minflt += current->min_flt; pacct->ac_majflt += current->maj_flt; spin_unlock_irq(¤t->sighand->siglock); diff --git a/kernel/cpu.c b/kernel/cpu.c index 3046a503242c..e5d5e8e1e030 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -224,11 +224,13 @@ void clear_tasks_mm_cpumask(int cpu) static inline void check_for_tasks(int cpu) { struct task_struct *p; + cputime_t utime, stime; write_lock_irq(&tasklist_lock); for_each_process(p) { + task_cputime(p, &utime, &stime); if (task_cpu(p) == cpu && p->state == TASK_RUNNING && - (p->utime || p->stime)) + (utime || stime)) printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d " "(state = %ld, flags = %x)\n", p->comm, task_pid_nr(p), cpu, diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 418b3f7053aa..d473988c1d0b 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -106,6 +106,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) unsigned long long t2, t3; unsigned long flags; struct timespec ts; + cputime_t utime, stime, stimescaled, utimescaled; /* Though tsk->delays accessed later, early exit avoids * unnecessary returning of other data @@ -114,12 +115,14 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) goto done; tmp = (s64)d->cpu_run_real_total; - cputime_to_timespec(tsk->utime + tsk->stime, &ts); + task_cputime(tsk, &utime, &stime); + cputime_to_timespec(utime + stime, &ts); tmp += timespec_to_ns(&ts); d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp; tmp = (s64)d->cpu_scaled_run_real_total; - cputime_to_timespec(tsk->utimescaled + tsk->stimescaled, &ts); + task_cputime_scaled(tsk, &utimescaled, &stimescaled); + cputime_to_timespec(utimescaled + stimescaled, &ts); tmp += timespec_to_ns(&ts); d->cpu_scaled_run_real_total = (tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp; diff --git a/kernel/exit.c b/kernel/exit.c index b4df21937216..7dd20408707c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -85,6 +85,7 @@ static void __exit_signal(struct task_struct *tsk) bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *uninitialized_var(tty); + cputime_t utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); @@ -123,9 +124,10 @@ 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 += tsk->utime; - sig->stime += tsk->stime; - sig->gtime += tsk->gtime; + task_cputime(tsk, &utime, &stime); + sig->utime += utime; + sig->stime += stime; + sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; @@ -1092,7 +1094,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) sig = p->signal; psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; - psig->cgtime += p->gtime + sig->gtime + sig->cgtime; + psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index a278cad1d5d6..165d47698477 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -155,11 +155,19 @@ static void bump_cpu_timer(struct k_itimer *timer, static inline cputime_t prof_ticks(struct task_struct *p) { - return p->utime + p->stime; + cputime_t utime, stime; + + task_cputime(p, &utime, &stime); + + return utime + stime; } static inline cputime_t virt_ticks(struct task_struct *p) { - return p->utime; + cputime_t utime; + + task_cputime(p, &utime, NULL); + + return utime; } static int @@ -471,18 +479,23 @@ static void cleanup_timers(struct list_head *head, */ void posix_cpu_timers_exit(struct task_struct *tsk) { + cputime_t utime, stime; + add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); + task_cputime(tsk, &utime, &stime); cleanup_timers(tsk->cpu_timers, - tsk->utime, tsk->stime, tsk->se.sum_exec_runtime); + utime, stime, tsk->se.sum_exec_runtime); } void posix_cpu_timers_exit_group(struct task_struct *tsk) { struct signal_struct *const sig = tsk->signal; + cputime_t utime, stime; + task_cputime(tsk, &utime, &stime); cleanup_timers(tsk->signal->cpu_timers, - tsk->utime + sig->utime, tsk->stime + sig->stime, + utime + sig->utime, stime + sig->stime, tsk->se.sum_exec_runtime + sig->sum_sched_runtime); } @@ -1226,11 +1239,14 @@ static inline int task_cputime_expired(const struct task_cputime *sample, static inline int fastpath_timer_check(struct task_struct *tsk) { struct signal_struct *sig; + cputime_t utime, stime; + + task_cputime(tsk, &utime, &stime); if (!task_cputime_zero(&tsk->cputime_expires)) { struct task_cputime task_sample = { - .utime = tsk->utime, - .stime = tsk->stime, + .utime = utime, + .stime = stime, .sum_exec_runtime = tsk->se.sum_exec_runtime }; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index e1939d38bf73..c533deaf06d5 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -164,7 +164,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime, task_group_account_field(p, index, (__force u64) cputime); /* Account for user time used */ - acct_update_integrals(p); + acct_account_cputime(p); } /* @@ -214,7 +214,7 @@ void __account_system_time(struct task_struct *p, cputime_t cputime, task_group_account_field(p, index, (__force u64) cputime); /* Account for system time used */ - acct_update_integrals(p); + acct_account_cputime(p); } /* @@ -296,6 +296,7 @@ static __always_inline bool steal_account_process_tick(void) void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) { struct signal_struct *sig = tsk->signal; + cputime_t utime, stime; struct task_struct *t; times->utime = sig->utime; @@ -309,8 +310,9 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) t = tsk; do { - times->utime += t->utime; - times->stime += t->stime; + task_cputime(tsk, &utime, &stime); + times->utime += utime; + times->stime += stime; times->sum_exec_runtime += task_sched_runtime(t); } while_each_thread(tsk, t); out: @@ -588,11 +590,10 @@ static void cputime_adjust(struct task_cputime *curr, void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) { struct task_cputime cputime = { - .utime = p->utime, - .stime = p->stime, .sum_exec_runtime = p->se.sum_exec_runtime, }; + task_cputime(p, &cputime.utime, &cputime.stime); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } diff --git a/kernel/signal.c b/kernel/signal.c index 372771e948c2..776a45a3661b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1638,6 +1638,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig) unsigned long flags; struct sighand_struct *psig; bool autoreap = false; + cputime_t utime, stime; BUG_ON(sig == -1); @@ -1675,8 +1676,9 @@ bool do_notify_parent(struct task_struct *tsk, int sig) task_uid(tsk)); rcu_read_unlock(); - info.si_utime = cputime_to_clock_t(tsk->utime + tsk->signal->utime); - info.si_stime = cputime_to_clock_t(tsk->stime + tsk->signal->stime); + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime); + info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) @@ -1740,6 +1742,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; + cputime_t utime, stime; if (for_ptracer) { parent = tsk->parent; @@ -1758,8 +1761,9 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, info.si_uid = from_kuid_munged(task_cred_xxx(parent, user_ns), task_uid(tsk)); rcu_read_unlock(); - info.si_utime = cputime_to_clock_t(tsk->utime); - info.si_stime = cputime_to_clock_t(tsk->stime); + task_cputime(tsk, &utime, &stime); + info.si_utime = cputime_to_clock_t(utime); + info.si_stime = cputime_to_clock_t(stime); info.si_code = why; switch (why) { diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 625df0b44690..a1dd9a1b1327 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -32,6 +32,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, { const struct cred *tcred; struct timespec uptime, ts; + cputime_t utime, stime, utimescaled, stimescaled; u64 ac_etime; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); @@ -65,10 +66,15 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_ppid = pid_alive(tsk) ? task_tgid_nr_ns(rcu_dereference(tsk->real_parent), pid_ns) : 0; rcu_read_unlock(); - stats->ac_utime = cputime_to_usecs(tsk->utime); - stats->ac_stime = cputime_to_usecs(tsk->stime); - stats->ac_utimescaled = cputime_to_usecs(tsk->utimescaled); - stats->ac_stimescaled = cputime_to_usecs(tsk->stimescaled); + + task_cputime(tsk, &utime, &stime); + stats->ac_utime = cputime_to_usecs(utime); + stats->ac_stime = cputime_to_usecs(stime); + + task_cputime_scaled(tsk, &utimescaled, &stimescaled); + stats->ac_utimescaled = cputime_to_usecs(utimescaled); + stats->ac_stimescaled = cputime_to_usecs(stimescaled); + stats->ac_minflt = tsk->min_flt; stats->ac_majflt = tsk->maj_flt; @@ -115,11 +121,8 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) #undef KB #undef MB -/** - * acct_update_integrals - update mm integral fields in task_struct - * @tsk: task_struct for accounting - */ -void acct_update_integrals(struct task_struct *tsk) +static void __acct_update_integrals(struct task_struct *tsk, + cputime_t utime, cputime_t stime) { if (likely(tsk->mm)) { cputime_t time, dtime; @@ -128,7 +131,7 @@ void acct_update_integrals(struct task_struct *tsk) u64 delta; local_irq_save(flags); - time = tsk->stime + tsk->utime; + time = stime + utime; dtime = time - tsk->acct_timexpd; jiffies_to_timeval(cputime_to_jiffies(dtime), &value); delta = value.tv_sec; @@ -144,6 +147,27 @@ void acct_update_integrals(struct task_struct *tsk) } } +/** + * acct_update_integrals - update mm integral fields in task_struct + * @tsk: task_struct for accounting + */ +void acct_update_integrals(struct task_struct *tsk) +{ + cputime_t utime, stime; + + task_cputime(tsk, &utime, &stime); + __acct_update_integrals(tsk, utime, stime); +} + +/** + * acct_account_cputime - update mm integral after cputime update + * @tsk: task_struct for accounting + */ +void acct_account_cputime(struct task_struct *tsk) +{ + __acct_update_integrals(tsk, tsk->utime, tsk->stime); +} + /** * acct_clear_integrals - clear the mm integral fields in task_struct * @tsk: task_struct whose accounting fields are cleared -- cgit v1.2.3