From d2b176ed878d4d5fcc0bd35656dfd373f3702af9 Mon Sep 17 00:00:00 2001 From: Jes Sorensen Date: Tue, 28 Feb 2006 09:42:23 -0800 Subject: [IA64] sysctl option to silence unaligned trap warnings Allow sysadmin to disable all warnings about userland apps making unaligned accesses by using: # echo 1 > /proc/sys/kernel/ignore-unaligned-usertrap Rather than having to use prctl on a process by process basis. Default behaivour leaves the warnings enabled. Signed-off-by: Jes Sorensen Signed-off-by: Tony Luck --- kernel/sysctl.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c05a2b7125e1..acf6c1550f27 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -124,6 +124,10 @@ extern int sysctl_hz_timer; extern int acct_parm[]; #endif +#ifdef CONFIG_IA64 +extern int no_unaligned_warning; +#endif + static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t, ctl_table *, void **); static int proc_doutsstring(ctl_table *table, int write, struct file *filp, @@ -665,6 +669,16 @@ static ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, +#endif +#ifdef CONFIG_IA64 + { + .ctl_name = KERN_IA64_UNALIGNED, + .procname = "ignore-unaligned-usertrap", + .data = &no_unaligned_warning, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, #endif { .ctl_name = 0 } }; -- cgit v1.2.2 From 7f99f06f01aa9460b5a18f1b0e0900c90d0a84fc Mon Sep 17 00:00:00 2001 From: Stefan Seyfried Date: Thu, 2 Mar 2006 02:54:34 -0800 Subject: [PATCH] fix acpi_video_flags on x86-64 acpi_video_flags variable is unsigned long, so it should be set as such. This actually matters on x86-64. Signed-off-by: Stefan Seyfried Signed-off-by: Pavel Machek Cc: "Brown, Len" Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index acf6c1550f27..de2d9109194e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -667,7 +667,7 @@ static ctl_table kern_table[] = { .data = &acpi_video_flags, .maxlen = sizeof (unsigned long), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_doulongvec_minmax, }, #endif #ifdef CONFIG_IA64 -- cgit v1.2.2 From 685db65e422bfa523b8a9dacb5a658b42b254f05 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 2 Mar 2006 02:54:35 -0800 Subject: [PATCH] time_interpolator: Use readq_relaxed() instead of readq(). On some platforms readq performs additional work to make sure I/O is done in a coherent way. This is not needed for time retrieval as done by the time interpolator. So we can use readq_relaxed instead which will improve performance. It affects sparc64 and ia64 only. Apparently it makes a significant difference on ia64. Signed-off-by: Christoph Lameter Cc: john stultz Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/timer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/timer.c b/kernel/timer.c index fe3a9a9f8328..fc6646fd5aab 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1351,10 +1351,10 @@ static inline u64 time_interpolator_get_cycles(unsigned int src) return x(); case TIME_SOURCE_MMIO64 : - return readq((void __iomem *) time_interpolator->addr); + return readq_relaxed((void __iomem *)time_interpolator->addr); case TIME_SOURCE_MMIO32 : - return readl((void __iomem *) time_interpolator->addr); + return readl_relaxed((void __iomem *)time_interpolator->addr); default: return get_cycles(); } -- cgit v1.2.2 From 8ba7b0a14b2ec19583bedbcdbea7f1c5008fc922 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 6 Mar 2006 17:38:49 -0800 Subject: Add early-boot-safety check to cond_resched() Just to be safe, we should not trigger a conditional reschedule during the early boot sequence. We've historically done some questionable early on, and the safety warnings in __might_sleep() are generally turned off during that period, so there might be problems lurking. This affects CONFIG_PREEMPT_VOLUNTARY, which takes over might_sleep() to cause a voluntary conditional reschedule. Acked-by: Ingo Molnar Signed-off-by: Linus Torvalds --- kernel/sched.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 12d291bf3379..3454bb869fd0 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4028,6 +4028,8 @@ static inline void __cond_resched(void) */ if (unlikely(preempt_count())) return; + if (unlikely(system_state != SYSTEM_RUNNING)) + return; do { add_preempt_count(PREEMPT_ACTIVE); schedule(); -- cgit v1.2.2 From 69239749e1ac4f3496906aa4267cb9f61ce52c9c Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 6 Mar 2006 15:42:45 -0800 Subject: [PATCH] fix next_timer_interrupt() for hrtimer Also from Thomas Gleixner Function next_timer_interrupt() got broken with a recent patch 6ba1b91213e81aa92b5cf7539f7d2a94ff54947c as sys_nanosleep() was moved to hrtimer. This broke things as next_timer_interrupt() did not check hrtimer tree for next event. Function next_timer_interrupt() is needed with dyntick (CONFIG_NO_IDLE_HZ, VST) implementations, as the system can be in idle when next hrtimer event was supposed to happen. At least ARM and S390 currently use next_timer_interrupt(). Signed-off-by: Thomas Gleixner Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/hrtimer.c | 35 +++++++++++++++++++++++++++++++++++ kernel/timer.c | 16 ++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'kernel') diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 5ae51f1bc7c8..14bc9cfa6399 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -505,6 +505,41 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) return rem; } +#ifdef CONFIG_NO_IDLE_HZ +/** + * hrtimer_get_next_event - get the time until next expiry event + * + * Returns the delta to the next expiry event or KTIME_MAX if no timer + * is pending. + */ +ktime_t hrtimer_get_next_event(void) +{ + struct hrtimer_base *base = __get_cpu_var(hrtimer_bases); + ktime_t delta, mindelta = { .tv64 = KTIME_MAX }; + unsigned long flags; + int i; + + for (i = 0; i < MAX_HRTIMER_BASES; i++, base++) { + struct hrtimer *timer; + + spin_lock_irqsave(&base->lock, flags); + if (!base->first) { + spin_unlock_irqrestore(&base->lock, flags); + continue; + } + timer = rb_entry(base->first, struct hrtimer, node); + delta.tv64 = timer->expires.tv64; + spin_unlock_irqrestore(&base->lock, flags); + delta = ktime_sub(delta, base->get_time()); + if (delta.tv64 < mindelta.tv64) + mindelta.tv64 = delta.tv64; + } + if (mindelta.tv64 < 0) + mindelta.tv64 = 0; + return mindelta; +} +#endif + /** * hrtimer_init - initialize a timer to the given clock * diff --git a/kernel/timer.c b/kernel/timer.c index fc6646fd5aab..8256f3f5ec0d 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -489,9 +489,21 @@ unsigned long next_timer_interrupt(void) struct list_head *list; struct timer_list *nte; unsigned long expires; + unsigned long hr_expires = MAX_JIFFY_OFFSET; + ktime_t hr_delta; tvec_t *varray[4]; int i, j; + hr_delta = hrtimer_get_next_event(); + if (hr_delta.tv64 != KTIME_MAX) { + struct timespec tsdelta; + tsdelta = ktime_to_timespec(hr_delta); + hr_expires = timespec_to_jiffies(&tsdelta); + if (hr_expires < 3) + return hr_expires + jiffies; + } + hr_expires += jiffies; + base = &__get_cpu_var(tvec_bases); spin_lock(&base->t_base.lock); expires = base->timer_jiffies + (LONG_MAX >> 1); @@ -542,6 +554,10 @@ found: } } spin_unlock(&base->t_base.lock); + + if (time_before(hr_expires, expires)) + return hr_expires; + return expires; } #endif -- cgit v1.2.2 From 5aee405c662ca644980c184774277fc6d0769a84 Mon Sep 17 00:00:00 2001 From: Atsushi Nemoto Date: Mon, 6 Mar 2006 15:42:51 -0800 Subject: [PATCH] time: add barrier after updating jiffies_64 Add a compiler barrier so that we don't read jiffies before updating jiffies_64. Signed-off-by: Atsushi Nemoto Cc: Ralf Baechle Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/timer.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/timer.c b/kernel/timer.c index 8256f3f5ec0d..bf7c4193b936 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -941,6 +941,8 @@ static inline void update_times(void) void do_timer(struct pt_regs *regs) { jiffies_64++; + /* prevent loading jiffies before storing new jiffies_64 value. */ + barrier(); update_times(); softlockup_tick(regs); } -- cgit v1.2.2 From 81c29a857d3c8d6ea9c4f20d196c36bf0a07c615 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 7 Mar 2006 21:55:27 -0800 Subject: [PATCH] idle threads should have a sane ->timestamp value Idle threads should have a sane ->timestamp value, to avoid init kernel thread(s) from inheriting it and causing miscalculations in try_to_wake_up(). Reported-by: Mike Galbraith . Signed-off-by: Ingo Molnar Cc: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/sched.c b/kernel/sched.c index 3454bb869fd0..e82c99f1db64 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4335,6 +4335,7 @@ void __devinit init_idle(task_t *idle, int cpu) runqueue_t *rq = cpu_rq(cpu); unsigned long flags; + idle->timestamp = sched_clock(); idle->sleep_avg = 0; idle->array = NULL; idle->prio = MAX_PRIO; -- cgit v1.2.2 From 21a1ea9eb40411d4ee29448c53b9e4c0654d6ceb Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Tue, 7 Mar 2006 21:55:33 -0800 Subject: [PATCH] rcu batch tuning This patch adds new tunables for RCU queue and finished batches. There are two types of controls - number of completed RCU updates invoked in a batch (blimit) and monitoring for high rate of incoming RCUs on a cpu (qhimark, qlowmark). By default, the per-cpu batch limit is set to a small value. If the input RCU rate exceeds the high watermark, we do two things - force quiescent state on all cpus and set the batch limit of the CPU to INTMAX. Setting batch limit to INTMAX forces all finished RCUs to be processed in one shot. If we have more than INTMAX RCUs queued up, then we have bigger problems anyway. Once the incoming queued RCUs fall below the low watermark, the batch limit is set to the default. Signed-off-by: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/rcupdate.c | 76 ++++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 58 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 0cf8146bd585..8cf15a569fcd 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -67,7 +67,43 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L }; /* Fake initialization required by compiler */ static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL}; -static int maxbatch = 10000; +static int blimit = 10; +static int qhimark = 10000; +static int qlowmark = 100; +#ifdef CONFIG_SMP +static int rsinterval = 1000; +#endif + +static atomic_t rcu_barrier_cpu_count; +static struct semaphore rcu_barrier_sema; +static struct completion rcu_barrier_completion; + +#ifdef CONFIG_SMP +static void force_quiescent_state(struct rcu_data *rdp, + struct rcu_ctrlblk *rcp) +{ + int cpu; + cpumask_t cpumask; + set_need_resched(); + if (unlikely(rdp->qlen - rdp->last_rs_qlen > rsinterval)) { + rdp->last_rs_qlen = rdp->qlen; + /* + * Don't send IPI to itself. With irqs disabled, + * rdp->cpu is the current cpu. + */ + cpumask = rcp->cpumask; + cpu_clear(rdp->cpu, cpumask); + for_each_cpu_mask(cpu, cpumask) + smp_send_reschedule(cpu); + } +} +#else +static inline void force_quiescent_state(struct rcu_data *rdp, + struct rcu_ctrlblk *rcp) +{ + set_need_resched(); +} +#endif /** * call_rcu - Queue an RCU callback for invocation after a grace period. @@ -92,17 +128,13 @@ void fastcall call_rcu(struct rcu_head *head, rdp = &__get_cpu_var(rcu_data); *rdp->nxttail = head; rdp->nxttail = &head->next; - - if (unlikely(++rdp->count > 10000)) - set_need_resched(); - + if (unlikely(++rdp->qlen > qhimark)) { + rdp->blimit = INT_MAX; + force_quiescent_state(rdp, &rcu_ctrlblk); + } local_irq_restore(flags); } -static atomic_t rcu_barrier_cpu_count; -static struct semaphore rcu_barrier_sema; -static struct completion rcu_barrier_completion; - /** * call_rcu_bh - Queue an RCU for invocation after a quicker grace period. * @head: structure to be used for queueing the RCU updates. @@ -131,12 +163,12 @@ void fastcall call_rcu_bh(struct rcu_head *head, rdp = &__get_cpu_var(rcu_bh_data); *rdp->nxttail = head; rdp->nxttail = &head->next; - rdp->count++; -/* - * Should we directly call rcu_do_batch() here ? - * if (unlikely(rdp->count > 10000)) - * rcu_do_batch(rdp); - */ + + if (unlikely(++rdp->qlen > qhimark)) { + rdp->blimit = INT_MAX; + force_quiescent_state(rdp, &rcu_bh_ctrlblk); + } + local_irq_restore(flags); } @@ -199,10 +231,12 @@ static void rcu_do_batch(struct rcu_data *rdp) next = rdp->donelist = list->next; list->func(list); list = next; - rdp->count--; - if (++count >= maxbatch) + rdp->qlen--; + if (++count >= rdp->blimit) break; } + if (rdp->blimit == INT_MAX && rdp->qlen <= qlowmark) + rdp->blimit = blimit; if (!rdp->donelist) rdp->donetail = &rdp->donelist; else @@ -473,6 +507,7 @@ static void rcu_init_percpu_data(int cpu, struct rcu_ctrlblk *rcp, rdp->quiescbatch = rcp->completed; rdp->qs_pending = 0; rdp->cpu = cpu; + rdp->blimit = blimit; } static void __devinit rcu_online_cpu(int cpu) @@ -567,7 +602,12 @@ void synchronize_kernel(void) synchronize_rcu(); } -module_param(maxbatch, int, 0); +module_param(blimit, int, 0); +module_param(qhimark, int, 0); +module_param(qlowmark, int, 0); +#ifdef CONFIG_SMP +module_param(rsinterval, int, 0); +#endif EXPORT_SYMBOL_GPL(rcu_batches_completed); EXPORT_SYMBOL(call_rcu); /* WARNING: GPL-only in April 2006. */ EXPORT_SYMBOL(call_rcu_bh); /* WARNING: GPL-only in April 2006. */ -- cgit v1.2.2 From 529bf6be5c04f2e869d07bfdb122e9fd98ade714 Mon Sep 17 00:00:00 2001 From: Dipankar Sarma Date: Tue, 7 Mar 2006 21:55:35 -0800 Subject: [PATCH] fix file counting I have benchmarked this on an x86_64 NUMA system and see no significant performance difference on kernbench. Tested on both x86_64 and powerpc. The way we do file struct accounting is not very suitable for batched freeing. For scalability reasons, file accounting was constructor/destructor based. This meant that nr_files was decremented only when the object was removed from the slab cache. This is susceptible to slab fragmentation. With RCU based file structure, consequent batched freeing and a test program like Serge's, we just speed this up and end up with a very fragmented slab - llm22:~ # cat /proc/sys/fs/file-nr 587730 0 758844 At the same time, I see only a 2000+ objects in filp cache. The following patch I fixes this problem. This patch changes the file counting by removing the filp_count_lock. Instead we use a separate percpu counter, nr_files, for now and all accesses to it are through get_nr_files() api. In the sysctl handler for nr_files, we populate files_stat.nr_files before returning to user. Counting files as an when they are created and destroyed (as opposed to inside slab) allows us to correctly count open files with RCU. Signed-off-by: Dipankar Sarma Cc: "Paul E. McKenney" Cc: "David S. Miller" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index de2d9109194e..32b48e8ee36e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -50,6 +50,9 @@ #include #include +extern int proc_nr_files(ctl_table *table, int write, struct file *filp, + void __user *buffer, size_t *lenp, loff_t *ppos); + #if defined(CONFIG_SYSCTL) /* External variables not in a header file. */ @@ -943,7 +946,7 @@ static ctl_table fs_table[] = { .data = &files_stat, .maxlen = 3*sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = &proc_nr_files, }, { .ctl_name = FS_MAXFILE, -- cgit v1.2.2