From aa2bf9bc6414b6972b9e51903c1ce7b1f057aee2 Mon Sep 17 00:00:00 2001 From: Sasikantha babu Date: Wed, 21 Mar 2012 20:10:54 +0530 Subject: itimer: Schedule silent NULL pointer fixup in setitimer() for removal setitimer() should return -EFAULT if called with an invalid pointer for value. The current code excludes a NULL pointer from this rule and silently uses it to stop the timer. This violates the spec. Warn about user space apps which rely on that feature and schedule it for removal. [ tglx: Massaged changelog, warn message and Doc entry ] Signed-off-by: Sasikantha babu Link: http://lkml.kernel.org/r/1332340854-26053-1-git-send-email-sasikanth.v19@gmail.com Signed-off-by: Thomas Gleixner diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 0cad480..32fae81 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -529,3 +529,11 @@ When: 3.5 Why: The old kmap_atomic() with two arguments is deprecated, we only keep it for backward compatibility for few cycles and then drop it. Who: Cong Wang + +---------------------------- + +What: setitimer accepts user NULL pointer (value) +When: 3.6 +Why: setitimer is not returning -EFAULT if user pointer is NULL. This + violates the spec. +Who: Sasikantha Babu diff --git a/kernel/itimer.c b/kernel/itimer.c index 22000c3..c70369a 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -284,8 +284,11 @@ SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value, if (value) { if(copy_from_user(&set_buffer, value, sizeof(set_buffer))) return -EFAULT; - } else + } else { memset((char *) &set_buffer, 0, sizeof(set_buffer)); + WARN_ONCE(1, "setitimer: new_value pointer is NULL." + " Misfeature support will be removed\n"); + } error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL); if (error || !ovalue) -- cgit v0.10.2 From cb85a6ed67e979c59a29b7b4e8217e755b951cf4 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 30 Mar 2012 12:23:08 +0200 Subject: proc: stats: Use arch_idle_time for idle and iowait times if available Git commit a25cac5198d4ff28 "proc: Consider NO_HZ when printing idle and iowait times" changes the code for /proc/stat to use get_cpu_idle_time_us and get_cpu_iowait_time_us if the system is running with nohz enabled. For architectures which define arch_idle_time (currently s390 only) this is a change for the worse. The result of arch_idle_time is supposed to be the exact sleep time of the target cpu and should be used instead of the value kept by the scheduler. Signed-off-by: Martin Schwidefsky Reviewed-by: Michal Hocko Reviewed-by: Srivatsa S. Bhat Link: http://lkml.kernel.org/r/20120330122308.18720283@de.ibm.com Signed-off-by: Thomas Gleixner diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 6a0c62d..64c3b31 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -18,19 +18,39 @@ #ifndef arch_irq_stat #define arch_irq_stat() 0 #endif -#ifndef arch_idle_time -#define arch_idle_time(cpu) 0 -#endif + +#ifdef arch_idle_time + +static cputime64_t get_idle_time(int cpu) +{ + cputime64_t idle; + + idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + if (cpu_online(cpu) && !nr_iowait_cpu(cpu)) + idle += arch_idle_time(cpu); + return idle; +} + +static cputime64_t get_iowait_time(int cpu) +{ + cputime64_t iowait; + + iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + if (cpu_online(cpu) && nr_iowait_cpu(cpu)) + iowait += arch_idle_time(cpu); + return iowait; +} + +#else static u64 get_idle_time(int cpu) { u64 idle, idle_time = get_cpu_idle_time_us(cpu, NULL); - if (idle_time == -1ULL) { + if (idle_time == -1ULL) /* !NO_HZ so we can rely on cpustat.idle */ idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; - idle += arch_idle_time(cpu); - } else + else idle = usecs_to_cputime64(idle_time); return idle; @@ -49,6 +69,8 @@ static u64 get_iowait_time(int cpu) return iowait; } +#endif + static int show_stat(struct seq_file *p, void *v) { int i, j; -- cgit v0.10.2 From 3872c48b14259d8c0a00c9fff06a4a4123f7f4eb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 31 Mar 2012 12:45:43 +0200 Subject: tick: Document TICK_ONESHOT config option This option has been selected from arch code as it was assumed that it's necessary to support oneshot mode clockevent devices. But it's just a core internal helper to compile tick-oneshot.c if NOHZ or HIG_RES_TIMERS are selected. Reported-by: Russell King Signed-off-by: Thomas Gleixner diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 2cf9cc7..a20dc8a 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -1,6 +1,10 @@ # # Timer subsystem related configuration options # + +# Core internal switch. Selected by NO_HZ / HIGH_RES_TIMERS. This is +# only related to the tick functionality. Oneshot clockevent devices +# are supported independ of this. config TICK_ONESHOT bool -- cgit v0.10.2 From 6f103929f8979d2638e58d7f7fda0beefcb8ee7e Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Tue, 27 Mar 2012 15:09:37 -0400 Subject: nohz: Fix stale jiffies update in tick_nohz_restart() Fix tick_nohz_restart() to not use a stale ktime_t "now" value when calling tick_do_update_jiffies64(now). If we reach this point in the loop it means that we crossed a tick boundary since we grabbed the "now" timestamp, so at this point "now" refers to a time in the old jiffy, so using the old value for "now" is incorrect, and is likely to give us a stale jiffies value. In particular, the first time through the loop the tick_do_update_jiffies64(now) call is always a no-op, since the caller, tick_nohz_restart_sched_tick(), will have already called tick_do_update_jiffies64(now) with that "now" value. Note that tick_nohz_stop_sched_tick() already uses the correct approach: when we notice we cross a jiffy boundary, grab a new timestamp with ktime_get(), and *then* update jiffies. Signed-off-by: Neal Cardwell Cc: Ben Segall Cc: Ingo Molnar Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1332875377-23014-1-git-send-email-ncardwell@google.com Signed-off-by: Thomas Gleixner diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 3526038..6a3a5b9 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -534,9 +534,9 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) hrtimer_get_expires(&ts->sched_timer), 0)) break; } - /* Update jiffies and reread time */ - tick_do_update_jiffies64(now); + /* Reread time and update jiffies */ now = ktime_get(); + tick_do_update_jiffies64(now); } } -- cgit v0.10.2 From 9886f444129171569461d8c39983e16f4871e3b4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Apr 2012 10:50:55 +0200 Subject: itimer: Use printk_once instead of WARN_ONCE David pointed out, that WARN_ONCE() to report usage of an deprecated misfeature make folks unhappy. Use printk_once() instead. Andrew told me to stop grumbling and to remove the silly typecast while touching the file. Reported-by: David Rientjes Cc: Andrew Morton Signed-off-by: Thomas Gleixner diff --git a/kernel/itimer.c b/kernel/itimer.c index c70369a..8d262b4 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -285,9 +285,10 @@ SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value, if(copy_from_user(&set_buffer, value, sizeof(set_buffer))) return -EFAULT; } else { - memset((char *) &set_buffer, 0, sizeof(set_buffer)); - WARN_ONCE(1, "setitimer: new_value pointer is NULL." - " Misfeature support will be removed\n"); + memset(&set_buffer, 0, sizeof(set_buffer)); + printk_once(KERN_WARNING "%s calls setitimer() with new_value NULL pointer." + " Misfeature support will be removed\n", + current->comm); } error = do_setitimer(which, &set_buffer, ovalue ? &get_buffer : NULL); -- cgit v0.10.2 From fa4da365bc7772c2cd6d5405bdf151612455f957 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 9 Apr 2012 15:41:44 -0700 Subject: clockevents: tTack broadcast device mode change in tick_broadcast_switch_to_oneshot() In the commit 77b0d60c5adf39c74039e2142a1d3cd1e4d53799, "clockevents: Leave the broadcast device in shutdown mode when not needed", we were bailing out too quickly in tick_broadcast_switch_to_oneshot(), with out tracking the broadcast device mode change to 'TICKDEV_MODE_ONESHOT'. This breaks the platforms which need broadcast device oneshot services during deep idle states. tick_broadcast_oneshot_control() thinks that it is in periodic mode and fails to take proper decisions based on the CLOCK_EVT_NOTIFY_BROADCAST_[ENTER, EXIT] notifications during deep idle entry/exit. Fix this by tracking the broadcast device mode as 'TICKDEV_MODE_ONESHOT', before leaving the broadcast HW device in shutdown mode if there are no active requests for the moment. Reported-and-tested-by: Santosh Shilimkar Signed-off-by: Suresh Siddha Cc: johnstul@us.ibm.com Link: http://lkml.kernel.org/r/1334011304.12400.81.camel@sbsiddha-desk.sc.intel.com Signed-off-by: Thomas Gleixner diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index e883f57..bf57abd 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -575,10 +575,12 @@ void tick_broadcast_switch_to_oneshot(void) unsigned long flags; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); + + tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; + if (cpumask_empty(tick_get_broadcast_mask())) goto end; - tick_broadcast_device.mode = TICKDEV_MODE_ONESHOT; bc = tick_broadcast_device.evtdev; if (bc) tick_broadcast_setup_oneshot(bc); -- cgit v0.10.2 From d48fc63f6f3f485ed5aa9cf019d8e8e3a7d10263 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 11 Apr 2012 23:49:16 +0200 Subject: Revert "clocksource: Load the ACPI PM clocksource asynchronously" This reverts commit b519508298e0292e1771eecf14aaf67755adc39d. The reason for this revert is that making the frequency verification preemptible and interruptible is not working reliably. Michaels machine failed to use PM-timer with the message: PM-Timer running at invalid rate: 113% of normal - aborting. That's not a surprise as the frequency verification does rely on interrupts being disabled. With a async scheduled thread there is no guarantee to achieve the same result. Also some driver might fiddle with the CTC channel 2 during the verification period, which makes the result even more random and unpredictable. This can be solved by using the same mechanism as we use in the deferred TSC validation code, but that only will work if we verified a working HPET _BEFORE_ trying to do the PM-Timer lazy validation. So for now reverting is the safe option. Bisected-by: Michael Witten Cc: Arjan van de Ven Cc: Arjan van de Ven Cc: John Stultz Cc: Len Brown LKML-Reference: Signed-off-by: Thomas Gleixner diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index 82e8820..6b5cf02 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -23,7 +23,6 @@ #include #include #include -#include #include /* @@ -180,15 +179,17 @@ static int verify_pmtmr_rate(void) /* Number of reads we try to get two different values */ #define ACPI_PM_READ_CHECKS 10000 -static void __init acpi_pm_clocksource_async(void *unused, async_cookie_t cookie) +static int __init init_acpi_pm_clocksource(void) { cycle_t value1, value2; unsigned int i, j = 0; + if (!pmtmr_ioport) + return -ENODEV; /* "verify" this timing source: */ for (j = 0; j < ACPI_PM_MONOTONICITY_CHECKS; j++) { - usleep_range(100 * j, 100 * j + 100); + udelay(100 * j); value1 = clocksource_acpi_pm.read(&clocksource_acpi_pm); for (i = 0; i < ACPI_PM_READ_CHECKS; i++) { value2 = clocksource_acpi_pm.read(&clocksource_acpi_pm); @@ -202,34 +203,25 @@ static void __init acpi_pm_clocksource_async(void *unused, async_cookie_t cookie " 0x%#llx, 0x%#llx - aborting.\n", value1, value2); pmtmr_ioport = 0; - return; + return -EINVAL; } if (i == ACPI_PM_READ_CHECKS) { printk(KERN_INFO "PM-Timer failed consistency check " " (0x%#llx) - aborting.\n", value1); pmtmr_ioport = 0; - return; + return -ENODEV; } } if (verify_pmtmr_rate() != 0){ pmtmr_ioport = 0; - return; + return -ENODEV; } - clocksource_register_hz(&clocksource_acpi_pm, + return clocksource_register_hz(&clocksource_acpi_pm, PMTMR_TICKS_PER_SEC); } -static int __init init_acpi_pm_clocksource(void) -{ - if (!pmtmr_ioport) - return -ENODEV; - - async_schedule(acpi_pm_clocksource_async, NULL); - return 0; -} - /* We use fs_initcall because we want the PCI fixups to have run * but we still need to load before device_initcall */ -- cgit v0.10.2