From b6276f353bf490add62dcf7db0ebd75baa3e1a37 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 6 Apr 2009 11:45:03 +0200 Subject: [PATCH] perf_counter: x86: self-IPI for pending work Implement set_perf_counter_pending() with a self-IPI so that it will run ASAP in a usable context. For now use a second IRQ vector, because the primary vector pokes the apic in funny ways that seem to confuse things. Signed-off-by: Peter Zijlstra Cc: Paul Mackerras Cc: Corey Ashford LKML-Reference: <20090406094517.724626696@chello.nl> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/entry_arch.h | 1 + arch/x86/include/asm/hardirq.h | 1 + arch/x86/include/asm/hw_irq.h | 1 + arch/x86/include/asm/irq_vectors.h | 5 +++++ arch/x86/include/asm/perf_counter.h | 3 ++- arch/x86/kernel/cpu/perf_counter.c | 14 ++++++++++++++ arch/x86/kernel/entry_64.S | 2 ++ arch/x86/kernel/irq.c | 5 +++++ arch/x86/kernel/irqinit_32.c | 1 + arch/x86/kernel/irqinit_64.c | 1 + 10 files changed, 33 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index c2e6bedaf258..fe24d2802490 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -50,6 +50,7 @@ BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR) #ifdef CONFIG_PERF_COUNTERS BUILD_INTERRUPT(perf_counter_interrupt, LOCAL_PERF_VECTOR) +BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR) #endif #ifdef CONFIG_X86_MCE_P4THERMAL diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 25454427ceea..f5ebe2aaca4b 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -14,6 +14,7 @@ typedef struct { #endif unsigned int generic_irqs; /* arch dependent */ unsigned int apic_perf_irqs; + unsigned int apic_pending_irqs; #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index ae80f64973e0..7309c0ad6902 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -30,6 +30,7 @@ extern void apic_timer_interrupt(void); extern void generic_interrupt(void); extern void error_interrupt(void); extern void perf_counter_interrupt(void); +extern void perf_pending_interrupt(void); extern void spurious_interrupt(void); extern void thermal_interrupt(void); diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 3cbd79bbb47c..545bb811ccb5 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -116,6 +116,11 @@ */ #define GENERIC_INTERRUPT_VECTOR 0xed +/* + * Performance monitoring pending work vector: + */ +#define LOCAL_PENDING_VECTOR 0xec + /* * First APIC vector available to drivers: (vectors 0x30-0xee) we * start at 0x31(0x41) to spread out vectors evenly between priority diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h index e2b0e66b2353..d08dd52cb8ff 100644 --- a/arch/x86/include/asm/perf_counter.h +++ b/arch/x86/include/asm/perf_counter.h @@ -84,7 +84,8 @@ union cpuid10_edx { #define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b #define X86_PMC_IDX_FIXED_BUS_CYCLES (X86_PMC_IDX_FIXED + 2) -#define set_perf_counter_pending() do { } while (0) +extern void set_perf_counter_pending(void); + #define clear_perf_counter_pending() do { } while (0) #define test_perf_counter_pending() (0) diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c index c74e20d593a7..438415866fe4 100644 --- a/arch/x86/kernel/cpu/perf_counter.c +++ b/arch/x86/kernel/cpu/perf_counter.c @@ -849,6 +849,20 @@ void smp_perf_counter_interrupt(struct pt_regs *regs) irq_exit(); } +void smp_perf_pending_interrupt(struct pt_regs *regs) +{ + irq_enter(); + ack_APIC_irq(); + inc_irq_stat(apic_pending_irqs); + perf_counter_do_pending(); + irq_exit(); +} + +void set_perf_counter_pending(void) +{ + apic->send_IPI_self(LOCAL_PENDING_VECTOR); +} + void perf_counters_lapic_init(int nmi) { u32 apic_val; diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 3f129d963a05..1d46cba56fd8 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -1028,6 +1028,8 @@ apicinterrupt SPURIOUS_APIC_VECTOR \ #ifdef CONFIG_PERF_COUNTERS apicinterrupt LOCAL_PERF_VECTOR \ perf_counter_interrupt smp_perf_counter_interrupt +apicinterrupt LOCAL_PENDING_VECTOR \ + perf_pending_interrupt smp_perf_pending_interrupt #endif /* diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 9c2754302ecc..d465487da587 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -67,6 +67,10 @@ static int show_other_interrupts(struct seq_file *p, int prec) for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs); seq_printf(p, " Performance counter interrupts\n"); + seq_printf(p, "PND: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs); + seq_printf(p, " Performance pending work\n"); #endif if (generic_interrupt_extension) { seq_printf(p, "PLT: "); @@ -171,6 +175,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->apic_timer_irqs; sum += irq_stats(cpu)->irq_spurious_count; sum += irq_stats(cpu)->apic_perf_irqs; + sum += irq_stats(cpu)->apic_pending_irqs; #endif if (generic_interrupt_extension) sum += irq_stats(cpu)->generic_irqs; diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c index 925d87cfc551..3190a6b961e6 100644 --- a/arch/x86/kernel/irqinit_32.c +++ b/arch/x86/kernel/irqinit_32.c @@ -166,6 +166,7 @@ static void __init apic_intr_init(void) alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); # ifdef CONFIG_PERF_COUNTERS alloc_intr_gate(LOCAL_PERF_VECTOR, perf_counter_interrupt); + alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt); # endif # ifdef CONFIG_X86_MCE_P4THERMAL diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index 665e2ab48abd..53ceb26f80ff 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -156,6 +156,7 @@ static void __init apic_intr_init(void) /* Performance monitoring interrupt: */ #ifdef CONFIG_PERF_COUNTERS alloc_intr_gate(LOCAL_PERF_VECTOR, perf_counter_interrupt); + alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt); #endif } -- 2.39.5