From 80a05b9ffa7dc13f6693902dd8999a2b61a3a0d7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 12 Mar 2010 17:34:14 +0100 Subject: clockevents: Sanitize min_delta_ns adjustment and prevent overflows The current logic which handles clock events programming failures can increase min_delta_ns unlimited and even can cause overflows. Sanitize it by: - prevent zero increase when min_delta_ns == 1 - limiting min_delta_ns to a jiffie - bail out if the jiffie limit is hit - add retries stats for /proc/timer_list so we can gather data Reported-by: Uwe Kleine-Koenig Signed-off-by: Thomas Gleixner --- kernel/time/tick-oneshot.c | 52 +++++++++++++++++++++++++++++++++++----------- kernel/time/timer_list.c | 3 ++- 2 files changed, 42 insertions(+), 13 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 0a8a213..aada0e5 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -22,6 +22,29 @@ #include "tick-internal.h" +/* Limit min_delta to a jiffie */ +#define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) + +static int tick_increase_min_delta(struct clock_event_device *dev) +{ + /* Nothing to do if we already reached the limit */ + if (dev->min_delta_ns >= MIN_DELTA_LIMIT) + return -ETIME; + + if (dev->min_delta_ns < 5000) + dev->min_delta_ns = 5000; + else + dev->min_delta_ns += dev->min_delta_ns >> 1; + + if (dev->min_delta_ns > MIN_DELTA_LIMIT) + dev->min_delta_ns = MIN_DELTA_LIMIT; + + printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", + dev->name ? dev->name : "?", + (unsigned long long) dev->min_delta_ns); + return 0; +} + /** * tick_program_event internal worker function */ @@ -37,23 +60,28 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires, if (!ret || !force) return ret; + dev->retries++; /* - * We tried 2 times to program the device with the given - * min_delta_ns. If that's not working then we double it + * We tried 3 times to program the device with the given + * min_delta_ns. If that's not working then we increase it * and emit a warning. */ if (++i > 2) { /* Increase the min. delta and try again */ - if (!dev->min_delta_ns) - dev->min_delta_ns = 5000; - else - dev->min_delta_ns += dev->min_delta_ns >> 1; - - printk(KERN_WARNING - "CE: %s increasing min_delta_ns to %llu nsec\n", - dev->name ? dev->name : "?", - (unsigned long long) dev->min_delta_ns << 1); - + if (tick_increase_min_delta(dev)) { + /* + * Get out of the loop if min_delta_ns + * hit the limit already. That's + * better than staying here forever. + * + * We clear next_event so we have a + * chance that the box survives. + */ + printk(KERN_WARNING + "CE: Reprogramming failure. Giving up\n"); + dev->next_event.tv64 = KTIME_MAX; + return -ETIME; + } i = 0; } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index bdfb8dd..1a4a7dd 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -228,6 +228,7 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) SEQ_printf(m, " event_handler: "); print_name_offset(m, dev->event_handler); SEQ_printf(m, "\n"); + SEQ_printf(m, " retries: %lu\n", dev->retries); } static void timer_list_show_tickdevices(struct seq_file *m) @@ -257,7 +258,7 @@ static int timer_list_show(struct seq_file *m, void *v) u64 now = ktime_to_ns(ktime_get()); int cpu; - SEQ_printf(m, "Timer List Version: v0.5\n"); + SEQ_printf(m, "Timer List Version: v0.6\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); -- cgit v1.1 From 830ec0458c390f29c6c99e1ff7feab9e36368d12 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 18 Mar 2010 14:47:30 -0700 Subject: time: Fix accumulation bug triggered by long delay. The logarithmic accumulation done in the timekeeping has some overflow protection that limits the max shift value. That means it will take more then shift loops to accumulate all of the cycles. This causes the shift decrement to underflow, which causes the loop to never exit. The simplest fix would be simply to do a: if (shift) shift--; However that is not optimal, as we know the cycle offset is larger then the interval << shift, the above would make shift drop to zero, then we would be spinning for quite awhile accumulating at interval chunks at a time. Instead, this patch only decreases shift if the offset is smaller then cycle_interval << shift. This makes sure we accumulate using the largest chunks possible without overflowing tick_length, and limits the number of iterations through the loop. This issue was found and reported by Sonic Zhang, who also tested the fix. Many thanks your explanation and testing! Reported-by: Sonic Zhang Signed-off-by: John Stultz Tested-by: Sonic Zhang LKML-Reference: <1268948850-5225-1-git-send-email-johnstul@us.ibm.com> Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/time') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1673637..39f6177 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -818,7 +818,8 @@ void update_wall_time(void) shift = min(shift, maxshift); while (offset >= timekeeper.cycle_interval) { offset = logarithmic_accumulation(offset, shift); - shift--; + if(offset < timekeeper.cycle_interval< Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- kernel/time/timecompare.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/time') diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c index 12f5c55..ac38fbb 100644 --- a/kernel/time/timecompare.c +++ b/kernel/time/timecompare.c @@ -19,6 +19,7 @@ #include #include +#include #include /* -- cgit v1.1