From 8c007bfdf1bab536f824d91fccc76596c18aba78 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 31 Jan 2010 20:30:23 +0000 Subject: powerpc: Reduce footprint of irq_stat PowerPC is currently using asm-generic/hardirq.h which statically allocates an NR_CPUS irq_stat array. Switch to an arch specific implementation which uses per cpu data: On a kernel with NR_CPUS=1024, this saves quite a lot of memory: text data bss dec hex filename 8767938 2944132 1636796 13348866 cbb002 vmlinux.baseline 8767779 2944260 1505724 13217763 c9afe3 vmlinux.irq_cpustat A saving of around 128kB. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/irq.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/kernel/irq.c') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 9040330b053..c6ac5583672 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -73,6 +73,9 @@ #define CREATE_TRACE_POINTS #include +DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); +EXPORT_PER_CPU_SYMBOL(irq_stat); + int __irq_offset_value; static int ppc_spurious_interrupts; -- cgit v1.2.3-70-g09d2 From c86845ede8b643ca025aec277dec1892d0ccac01 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 31 Jan 2010 20:33:18 +0000 Subject: powerpc: Rework /proc/interrupts On a large machine I noticed the columns of /proc/interrupts failed to line up with the header after CPU9. At sufficiently large numbers of CPUs it becomes impossible to line up the CPU number with the counts. While fixing this I noticed x86 has a number of updates that we may as well pull in. On PowerPC we currently omit an interrupt completely if there is no active handler, whereas on x86 it is printed if there is a non zero count. The x86 code also spaces the first column correctly based on nr_irqs. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/irq.c | 79 +++++++++++++++++++++++++++-------------------- 1 file changed, 46 insertions(+), 33 deletions(-) (limited to 'arch/powerpc/kernel/irq.c') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c6ac5583672..b9cbb457004 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -183,30 +183,46 @@ notrace void raw_local_irq_restore(unsigned long en) EXPORT_SYMBOL(raw_local_irq_restore); #endif /* CONFIG_PPC64 */ +static int show_other_interrupts(struct seq_file *p, int prec) +{ + int j; + +#if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT) + if (tau_initialized) { + seq_printf(p, "%*s: ", prec, "TAU"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", tau_interrupts(j)); + seq_puts(p, " PowerPC Thermal Assist (cpu temp)\n"); + } +#endif /* CONFIG_PPC32 && CONFIG_TAU_INT */ + + seq_printf(p, "%*s: %10u\n", prec, "BAD", ppc_spurious_interrupts); + + return 0; +} + int show_interrupts(struct seq_file *p, void *v) { - int i = *(loff_t *)v, j; + unsigned long flags, any_count = 0; + int i = *(loff_t *) v, j, prec; struct irqaction *action; struct irq_desc *desc; - unsigned long flags; + if (i > nr_irqs) + return 0; + + for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec) + j *= 10; + + if (i == nr_irqs) + return show_other_interrupts(p, prec); + + /* print header */ if (i == 0) { - seq_puts(p, " "); + seq_printf(p, "%*s", prec + 8, ""); for_each_online_cpu(j) - seq_printf(p, "CPU%d ", j); + seq_printf(p, "CPU%-8d", j); seq_putc(p, '\n'); - } else if (i == nr_irqs) { -#if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT) - if (tau_initialized){ - seq_puts(p, "TAU: "); - for_each_online_cpu(j) - seq_printf(p, "%10u ", tau_interrupts(j)); - seq_puts(p, " PowerPC Thermal Assist (cpu temp)\n"); - } -#endif /* CONFIG_PPC32 && CONFIG_TAU_INT*/ - seq_printf(p, "BAD: %10u\n", ppc_spurious_interrupts); - - return 0; } desc = irq_to_desc(i); @@ -214,34 +230,31 @@ int show_interrupts(struct seq_file *p, void *v) return 0; raw_spin_lock_irqsave(&desc->lock, flags); - + for_each_online_cpu(j) + any_count |= kstat_irqs_cpu(i, j); action = desc->action; - if (!action || !action->handler) - goto skip; + if (!action && !any_count) + goto out; - seq_printf(p, "%3d: ", i); -#ifdef CONFIG_SMP + seq_printf(p, "%*d: ", prec, i); for_each_online_cpu(j) seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); -#else - seq_printf(p, "%10u ", kstat_irqs(i)); -#endif /* CONFIG_SMP */ if (desc->chip) - seq_printf(p, " %s ", desc->chip->name); + seq_printf(p, " %-16s", desc->chip->name); else - seq_puts(p, " None "); + seq_printf(p, " %-16s", "None"); + seq_printf(p, " %-8s", (desc->status & IRQ_LEVEL) ? "Level" : "Edge"); - seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge "); - seq_printf(p, " %s", action->name); + if (action) { + seq_printf(p, " %s", action->name); + while ((action = action->next) != NULL) + seq_printf(p, ", %s", action->name); + } - for (action = action->next; action; action = action->next) - seq_printf(p, ", %s", action->name); seq_putc(p, '\n'); - -skip: +out: raw_spin_unlock_irqrestore(&desc->lock, flags); - return 0; } -- cgit v1.2.3-70-g09d2 From 89713ed10815401a1bfe12e3a076b64048381b56 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 31 Jan 2010 20:34:06 +0000 Subject: powerpc: Add timer, performance monitor and machine check counts to /proc/interrupts With NO_HZ it is useful to know how often the decrementer is going off. The patch below adds an entry for it and also adds it into the /proc/stat summaries. While here, I added performance monitoring and machine check exceptions. I found it useful to keep an eye on the PMU exception rate when using the perf tool. Since it's possible to take a completely handled machine check on a System p box it also sounds like a good idea to keep a machine check summary. The event naming matches x86 to keep gratuitous differences to a minimum. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hardirq.h | 9 +++++++++ arch/powerpc/kernel/irq.c | 35 +++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/time.c | 2 ++ arch/powerpc/kernel/traps.c | 4 ++++ 4 files changed, 50 insertions(+) (limited to 'arch/powerpc/kernel/irq.c') diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index 9bf3467581b..cd2d4be882a 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -6,6 +6,9 @@ typedef struct { unsigned int __softirq_pending; + unsigned int timer_irqs; + unsigned int pmu_irqs; + unsigned int mce_exceptions; } ____cacheline_aligned irq_cpustat_t; DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); @@ -19,4 +22,10 @@ static inline void ack_bad_irq(unsigned int irq) printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq); } +extern u64 arch_irq_stat_cpu(unsigned int cpu); +#define arch_irq_stat_cpu arch_irq_stat_cpu + +extern u64 arch_irq_stat(void); +#define arch_irq_stat arch_irq_stat + #endif /* _ASM_POWERPC_HARDIRQ_H */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index b9cbb457004..710505240f2 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -196,6 +196,21 @@ static int show_other_interrupts(struct seq_file *p, int prec) } #endif /* CONFIG_PPC32 && CONFIG_TAU_INT */ + seq_printf(p, "%*s: ", prec, "LOC"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs); + seq_printf(p, " Local timer interrupts\n"); + + seq_printf(p, "%*s: ", prec, "CNT"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs); + seq_printf(p, " Performance monitoring interrupts\n"); + + seq_printf(p, "%*s: ", prec, "MCE"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions); + seq_printf(p, " Machine check exceptions\n"); + seq_printf(p, "%*s: %10u\n", prec, "BAD", ppc_spurious_interrupts); return 0; @@ -258,6 +273,26 @@ out: return 0; } +/* + * /proc/stat helpers + */ +u64 arch_irq_stat_cpu(unsigned int cpu) +{ + u64 sum = per_cpu(irq_stat, cpu).timer_irqs; + + sum += per_cpu(irq_stat, cpu).pmu_irqs; + sum += per_cpu(irq_stat, cpu).mce_exceptions; + + return sum; +} + +u64 arch_irq_stat(void) +{ + u64 sum = ppc_spurious_interrupts; + + return sum; +} + #ifdef CONFIG_HOTPLUG_CPU void fixup_irqs(cpumask_t map) { diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index ed1c0f58344..1b16b9a3e49 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -575,6 +575,8 @@ void timer_interrupt(struct pt_regs * regs) trace_timer_interrupt_entry(regs); + __get_cpu_var(irq_stat).timer_irqs++; + /* Ensure a positive value is written to the decrementer, or else * some CPUs will continuue to take decrementer exceptions */ set_dec(DECREMENTER_MAX); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 0a320dbd950..895da29e7db 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -483,6 +483,8 @@ void machine_check_exception(struct pt_regs *regs) { int recover = 0; + __get_cpu_var(irq_stat).mce_exceptions++; + /* See if any machine dependent calls. In theory, we would want * to call the CPU first, and call the ppc_md. one if the CPU * one returns a positive number. However there is existing code @@ -965,6 +967,8 @@ void vsx_unavailable_exception(struct pt_regs *regs) void performance_monitor_exception(struct pt_regs *regs) { + __get_cpu_var(irq_stat).pmu_irqs++; + perf_irq(regs); } -- cgit v1.2.3-70-g09d2 From 17081102a6e0fe32cf47cdbdf8f2e9ab55273b08 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Sun, 31 Jan 2010 20:34:36 +0000 Subject: powerpc: Convert global "BAD" interrupt to per cpu spurious I often get asked if BAD interrupts are really bad. On some boxes (eg IBM machines running a hypervisor) there are valid cases where are presented with an interrupt that is not for us. These cases are common enough to show up as thousands of BAD interrupts a day. Tone them down by calling them spurious. Since they can be a significant cause of OS jitter, we may as well log them per cpu so we know where they are occurring. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/hardirq.h | 4 +--- arch/powerpc/kernel/irq.c | 19 +++++++------------ 2 files changed, 8 insertions(+), 15 deletions(-) (limited to 'arch/powerpc/kernel/irq.c') diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index cd2d4be882a..3147a297012 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -9,6 +9,7 @@ typedef struct { unsigned int timer_irqs; unsigned int pmu_irqs; unsigned int mce_exceptions; + unsigned int spurious_irqs; } ____cacheline_aligned irq_cpustat_t; DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); @@ -25,7 +26,4 @@ static inline void ack_bad_irq(unsigned int irq) extern u64 arch_irq_stat_cpu(unsigned int cpu); #define arch_irq_stat_cpu arch_irq_stat_cpu -extern u64 arch_irq_stat(void); -#define arch_irq_stat arch_irq_stat - #endif /* _ASM_POWERPC_HARDIRQ_H */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 710505240f2..9ae77e52f9d 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -77,7 +77,6 @@ DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); int __irq_offset_value; -static int ppc_spurious_interrupts; #ifdef CONFIG_PPC32 EXPORT_SYMBOL(__irq_offset_value); @@ -201,6 +200,11 @@ static int show_other_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", per_cpu(irq_stat, j).timer_irqs); seq_printf(p, " Local timer interrupts\n"); + seq_printf(p, "%*s: ", prec, "SPU"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs); + seq_printf(p, " Spurious interrupts\n"); + seq_printf(p, "%*s: ", prec, "CNT"); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs); @@ -211,8 +215,6 @@ static int show_other_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions); seq_printf(p, " Machine check exceptions\n"); - seq_printf(p, "%*s: %10u\n", prec, "BAD", ppc_spurious_interrupts); - return 0; } @@ -282,13 +284,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += per_cpu(irq_stat, cpu).pmu_irqs; sum += per_cpu(irq_stat, cpu).mce_exceptions; - - return sum; -} - -u64 arch_irq_stat(void) -{ - u64 sum = ppc_spurious_interrupts; + sum += per_cpu(irq_stat, cpu).spurious_irqs; return sum; } @@ -404,8 +400,7 @@ void do_IRQ(struct pt_regs *regs) if (irq != NO_IRQ && irq != NO_IRQ_IGNORE) handle_one_irq(irq); else if (irq != NO_IRQ_IGNORE) - /* That's not SMP safe ... but who cares ? */ - ppc_spurious_interrupts++; + __get_cpu_var(irq_stat).spurious_irqs++; irq_exit(); set_irq_regs(old_regs); -- cgit v1.2.3-70-g09d2 From f95e085b2531c86262b97a081eb0d1cf793606d3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 18 Feb 2010 02:22:24 +0000 Subject: powerpc: Convert big_irq_lock to raw_spinlock big_irq_lock needs to be a real spinlock in RT. Convert it to raw_spinlock. Signed-off-by: Thomas Gleixner Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/irq.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'arch/powerpc/kernel/irq.c') diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 9ae77e52f9d..64f6f2031c2 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -520,7 +520,7 @@ void do_softirq(void) */ static LIST_HEAD(irq_hosts); -static DEFINE_SPINLOCK(irq_big_lock); +static DEFINE_RAW_SPINLOCK(irq_big_lock); static unsigned int revmap_trees_allocated; static DEFINE_MUTEX(revmap_trees_mutex); struct irq_map_entry irq_map[NR_IRQS]; @@ -566,14 +566,14 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, if (host->ops->match == NULL) host->ops->match = default_irq_host_match; - spin_lock_irqsave(&irq_big_lock, flags); + raw_spin_lock_irqsave(&irq_big_lock, flags); /* If it's a legacy controller, check for duplicates and * mark it as allocated (we use irq 0 host pointer for that */ if (revmap_type == IRQ_HOST_MAP_LEGACY) { if (irq_map[0].host != NULL) { - spin_unlock_irqrestore(&irq_big_lock, flags); + raw_spin_unlock_irqrestore(&irq_big_lock, flags); /* If we are early boot, we can't free the structure, * too bad... * this will be fixed once slab is made available early @@ -587,7 +587,7 @@ struct irq_host *irq_alloc_host(struct device_node *of_node, } list_add(&host->link, &irq_hosts); - spin_unlock_irqrestore(&irq_big_lock, flags); + raw_spin_unlock_irqrestore(&irq_big_lock, flags); /* Additional setups per revmap type */ switch(revmap_type) { @@ -638,13 +638,13 @@ struct irq_host *irq_find_host(struct device_node *node) * the absence of a device node. This isn't a problem so far * yet though... */ - spin_lock_irqsave(&irq_big_lock, flags); + raw_spin_lock_irqsave(&irq_big_lock, flags); list_for_each_entry(h, &irq_hosts, link) if (h->ops->match(h, node)) { found = h; break; } - spin_unlock_irqrestore(&irq_big_lock, flags); + raw_spin_unlock_irqrestore(&irq_big_lock, flags); return found; } EXPORT_SYMBOL_GPL(irq_find_host); @@ -1013,7 +1013,7 @@ unsigned int irq_alloc_virt(struct irq_host *host, if (count == 0 || count > (irq_virq_count - NUM_ISA_INTERRUPTS)) return NO_IRQ; - spin_lock_irqsave(&irq_big_lock, flags); + raw_spin_lock_irqsave(&irq_big_lock, flags); /* Use hint for 1 interrupt if any */ if (count == 1 && hint >= NUM_ISA_INTERRUPTS && @@ -1037,7 +1037,7 @@ unsigned int irq_alloc_virt(struct irq_host *host, } } if (found == NO_IRQ) { - spin_unlock_irqrestore(&irq_big_lock, flags); + raw_spin_unlock_irqrestore(&irq_big_lock, flags); return NO_IRQ; } hint_found: @@ -1046,7 +1046,7 @@ unsigned int irq_alloc_virt(struct irq_host *host, smp_wmb(); irq_map[i].host = host; } - spin_unlock_irqrestore(&irq_big_lock, flags); + raw_spin_unlock_irqrestore(&irq_big_lock, flags); return found; } @@ -1058,7 +1058,7 @@ void irq_free_virt(unsigned int virq, unsigned int count) WARN_ON (virq < NUM_ISA_INTERRUPTS); WARN_ON (count == 0 || (virq + count) > irq_virq_count); - spin_lock_irqsave(&irq_big_lock, flags); + raw_spin_lock_irqsave(&irq_big_lock, flags); for (i = virq; i < (virq + count); i++) { struct irq_host *host; @@ -1071,7 +1071,7 @@ void irq_free_virt(unsigned int virq, unsigned int count) smp_wmb(); irq_map[i].host = NULL; } - spin_unlock_irqrestore(&irq_big_lock, flags); + raw_spin_unlock_irqrestore(&irq_big_lock, flags); } int arch_early_irq_init(void) -- cgit v1.2.3-70-g09d2