Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760796AbYHOQZu (ORCPT ); Fri, 15 Aug 2008 12:25:50 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1760570AbYHOQZg (ORCPT ); Fri, 15 Aug 2008 12:25:36 -0400 Received: from mx1.redhat.com ([66.187.233.31]:45593 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760443AbYHOQZd (ORCPT ); Fri, 15 Aug 2008 12:25:33 -0400 Date: Fri, 15 Aug 2008 12:25:03 -0400 Message-Id: <200808151625.m7FGP3Gn027609@int-mx1.corp.redhat.com> From: Glauber Costa To: mingo@elte.hu, tglx@linutronix.de, hpa@zytor.com, linux-kernel@vger.kernel.org, x86@kernel.org Subject: [GIT PULL] new shot at time.c integration Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 18142 Lines: 596 Ingo, please pull the latest master git tree from: git://git.kernel.org/pub/scm/linux/kernel/git/glommer/linux-2.6-x86-integration.git master into your tree It is based on your tip/master branch. This addresses the issues you raise in the last trial. In particular, I have a commit in the end that moves even comments and blank lines from time_32.c to time_64.c, making the files exactly equal prior to the merge. I also found a bug in earlier series, (it's always good when it's found in-house first, so good news!). This one should be good. Thanks! Glauber ------------------> Glauber Costa (32): x86: use user_mode macro x86: coalesce tests x86: set bp field in pt_regs properly x86: use frame pointer information on x86_64 profile_pc x86: remove SEGMENT_IS_FLAT_CODE x86: use user_mode_vm instead of user_mode x86: bind irq0 irq data to cpu0 x86: factor out irq initialization for x86_64 x86: make init_ISA_irqs nonstatic x86: rename timer_event_interrupt to timer_interrupt x86: allow x86_64 to build with subarch support x86: replace ISA initialization function x86: use generic intr_init call x86: use time_init_hook in time_64.c x86: use generic time hook x86: replace hardcoded number x86: add timer.h header to io_apic_64.c x86: unconditionalize timer_ack x86: assign timer_ack variable x86: wrap MCA_bus test around an ifdef x86: wrap conditional inside ifdef at profile_pc x86: fix checkpatch errors x86: move vgetcpu mode probing to cpu detection x86: add pre_time_init_hooks to x86_64 time initialization x86: conditionalize interrupt accounting x86: fix address reference x86: remove header from time_64.c x86: reorganize time_32.c headers x86: reorganize 64-bit only code x86: merge copyright notice x86: make time_64 and time_32 equal x86: merge time.c arch/x86/Makefile | 4 - arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/cpu/common_64.c | 9 +++ arch/x86/kernel/entry_64.S | 7 ++ arch/x86/kernel/io_apic_64.c | 6 ++- arch/x86/kernel/irqinit_64.c | 59 ++++++++-------- arch/x86/kernel/{time_32.c => time.c} | 79 +++++++++++++++++++-- arch/x86/kernel/time_64.c | 126 --------------------------------- include/asm-x86/segment.h | 6 -- include/asm-x86/timer.h | 2 +- 10 files changed, 124 insertions(+), 176 deletions(-) rename arch/x86/kernel/{time_32.c => time.c} (65%) delete mode 100644 arch/x86/kernel/time_64.c diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 58ea55c..3ead876 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -121,10 +121,6 @@ mcore-$(CONFIG_X86_GENERICARCH) := arch/x86/mach-default/ # default subarch .h files mflags-y += -Iinclude/asm-x86/mach-default -# 64 bit does not support subarch support - clear sub arch variables -fcore-$(CONFIG_X86_64) := -mcore-$(CONFIG_X86_64) := - KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 02654a4..6b1ad31 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -25,7 +25,7 @@ CFLAGS_paravirt.o := $(nostackp) obj-y := process_$(BITS).o signal_$(BITS).o entry_$(BITS).o obj-y += traps_$(BITS).o irq_$(BITS).o -obj-y += time_$(BITS).o ioport.o ldt.o +obj-y += time.o ioport.o ldt.o obj-y += setup.o i8259.o irqinit_$(BITS).o setup_percpu.o obj-$(CONFIG_X86_VISWS) += visws_quirks.o obj-$(CONFIG_X86_32) += probe_roms_32.o diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c index cc6efe8..5e0a760 100644 --- a/arch/x86/kernel/cpu/common_64.c +++ b/arch/x86/kernel/cpu/common_64.c @@ -375,9 +375,18 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) } +static void vgetcpu_set_mode(void) +{ + if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) + vgetcpu_mode = VGETCPU_RDTSCP; + else + vgetcpu_mode = VGETCPU_LSL; +} + void __cpuinit identify_boot_cpu(void) { identify_cpu(&boot_cpu_data); + vgetcpu_set_mode(); } void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 0ae162c..0602253 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -669,6 +669,13 @@ END(stub_rt_sigreturn) SAVE_ARGS leaq -ARGOFFSET(%rsp),%rdi # arg1 for handler pushq %rbp + /* + * Save rbp twice: One is for marking the stack frame, as usual, and the + * other, to fill pt_regs properly. This is because bx comes right + * before the last saved register in that structure, and not bp. If the + * base pointer were in the place bx is today, this would not be needed. + */ + movq %rbp, -8(%rsp) CFI_ADJUST_CFA_OFFSET 8 CFI_REL_OFFSET rbp, 0 movq %rsp,%rbp diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c index a1bec29..91e7c10 100644 --- a/arch/x86/kernel/io_apic_64.c +++ b/arch/x86/kernel/io_apic_64.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include @@ -93,7 +94,7 @@ char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE}; int sis_apic_bug; /* not actually supported, dummy for compile */ -static int no_timer_check; +int no_timer_check; static int disable_timer_pin_1 __initdata; @@ -2017,6 +2018,7 @@ static inline void __init check_timer(void) */ apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); init_8259A(1); + timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); pin1 = find_isa_irq_pin(0, mp_INT); apic1 = find_isa_irq_apic(0, mp_INT); @@ -2099,6 +2101,8 @@ static inline void __init check_timer(void) apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n"); } + timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver)); + if (nmi_watchdog == NMI_IO_APIC) { apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work " "through the IO-APIC - disabling NMI Watchdog!\n"); diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index 1f26fd9..92b5f2b 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -22,6 +22,7 @@ #include #include #include +#include /* * Common place to define all x86 IRQ vectors @@ -102,18 +103,6 @@ static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = #undef IRQ #undef IRQLIST_16 - - - -/* - * IRQ2 is cascade interrupt to second interrupt controller - */ - -static struct irqaction irq2 = { - .handler = no_action, - .mask = CPU_MASK_NONE, - .name = "cascade", -}; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... IRQ0_VECTOR - 1] = -1, [IRQ0_VECTOR] = 0, @@ -135,7 +124,7 @@ DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1 }; -static void __init init_ISA_irqs (void) +void __init init_ISA_irqs(void) { int i; @@ -164,22 +153,8 @@ static void __init init_ISA_irqs (void) void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ"))); -void __init native_init_IRQ(void) +void __init smp_intr_init(void) { - int i; - - init_ISA_irqs(); - /* - * Cover the whole vector space, no vector can escape - * us. (some of these will be overridden and become - * 'special' SMP interrupts) - */ - for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) { - int vector = FIRST_EXTERNAL_VECTOR + i; - if (vector != IA32_SYSCALL_VECTOR) - set_intr_gate(vector, interrupt[i]); - } - #ifdef CONFIG_SMP /* * The reschedule interrupt is a CPU-to-CPU reschedule-helper @@ -207,6 +182,14 @@ void __init native_init_IRQ(void) /* Low priority IPI to cleanup after moving an irq */ set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt); #endif +} + +void __init apic_intr_init(void) +{ +#ifdef CONFIG_SMP + smp_intr_init(); +#endif + alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt); alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); @@ -216,7 +199,23 @@ void __init native_init_IRQ(void) /* IPI vectors for APIC spurious and error interrupts */ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); +} + +void __init native_init_IRQ(void) +{ + int i; + + pre_intr_init_hook(); + /* + * Cover the whole vector space, no vector can escape + * us. (some of these will be overridden and become + * 'special' SMP interrupts) + */ + for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) { + int vector = FIRST_EXTERNAL_VECTOR + i; + if (vector != IA32_SYSCALL_VECTOR) + set_intr_gate(vector, interrupt[i]); + } - if (!acpi_ioapic) - setup_irq(2, &irq2); + intr_init_hook(); } diff --git a/arch/x86/kernel/time_32.c b/arch/x86/kernel/time.c similarity index 65% rename from arch/x86/kernel/time_32.c rename to arch/x86/kernel/time.c index bbecf8b..9e6e5fb 100644 --- a/arch/x86/kernel/time_32.c +++ b/arch/x86/kernel/time.c @@ -1,5 +1,6 @@ /* * Copyright (C) 1991, 1992, 1995 Linus Torvalds + * "High Precision Event Timer" based timekeeping. * * This file contains the PC-specific time handling details: * reading the RTC at bootup, etc.. @@ -26,17 +27,26 @@ * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to * serialize accesses to xtime/lost_ticks). + * + * Copyright (c) 2002,2006 Vojtech Pavlik + * Copyright (c) 2003 Andi Kleen + * Copyright (c) 2008 Glauber Costa - i386/x86_64 integration. + * + * RTC support code taken from arch/i386/kernel/timers/time_hpet.c */ +#include #include #include +#include #include #include -#include #include +#include #include #include +#include #include "do_timer.h" @@ -47,12 +57,11 @@ unsigned long profile_pc(struct pt_regs *regs) unsigned long pc = instruction_pointer(regs); #ifdef CONFIG_SMP - if (!v8086_mode(regs) && SEGMENT_IS_KERNEL_CODE(regs->cs) && - in_lock_functions(pc)) { + if (!user_mode_vm(regs) && in_lock_functions(pc)) { #ifdef CONFIG_FRAME_POINTER - return *(unsigned long *)(regs->bp + 4); + return *(unsigned long *)(regs->bp + sizeof(long)); #else - unsigned long *sp = (unsigned long *)®s->sp; + unsigned long *sp = (unsigned long *)regs->sp; /* Return address is either directly at stack pointer or above a saved flags. Eflags has bits 22-31 zero, @@ -75,8 +84,13 @@ EXPORT_SYMBOL(profile_pc); */ irqreturn_t timer_interrupt(int irq, void *dev_id) { + +#ifdef CONFIG_X86_32 /* Keep nmi watchdog up to date */ per_cpu(irq_stat, smp_processor_id()).irq0_irqs++; +#else + add_pda(irq0_irqs, 1); +#endif #ifdef CONFIG_X86_IO_APIC if (timer_ack) { @@ -95,6 +109,7 @@ irqreturn_t timer_interrupt(int irq, void *dev_id) do_timer_interrupt_hook(); +#ifdef CONFIG_MCA if (MCA_bus) { /* The PS/2 uses level-triggered interrupts. You can't turn them off, nor would you want to (any attempt to @@ -105,13 +120,63 @@ irqreturn_t timer_interrupt(int irq, void *dev_id) high bit of the PPI port B (0x61). Note that some PS/2s, notably the 55SX, work fine if this is removed. */ - u8 irq_v = inb_p( 0x61 ); /* read the current state */ - outb_p( irq_v|0x80, 0x61 ); /* reset the IRQ */ + u8 irq_v = inb_p(0x61); /* read the current state */ + outb_p(irq_v|0x80, 0x61); /* reset the IRQ */ } +#endif return IRQ_HANDLED; } +#ifdef CONFIG_X86_64 +volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; +/* calibrate_cpu is used on systems with fixed rate TSCs to determine + * processor frequency */ +#define TICK_COUNT 100000000 +unsigned long __init calibrate_cpu(void) +{ + int tsc_start, tsc_now; + int i, no_ctr_free; + unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0; + unsigned long flags; + + for (i = 0; i < 4; i++) + if (avail_to_resrv_perfctr_nmi_bit(i)) + break; + no_ctr_free = (i == 4); + if (no_ctr_free) { + i = 3; + rdmsrl(MSR_K7_EVNTSEL3, evntsel3); + wrmsrl(MSR_K7_EVNTSEL3, 0); + rdmsrl(MSR_K7_PERFCTR3, pmc3); + } else { + reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i); + reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } + local_irq_save(flags); + /* start measuring cycles, incrementing from 0 */ + wrmsrl(MSR_K7_PERFCTR0 + i, 0); + wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76); + rdtscl(tsc_start); + do { + rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now); + tsc_now = get_cycles(); + } while ((tsc_now - tsc_start) < TICK_COUNT); + + local_irq_restore(flags); + if (no_ctr_free) { + wrmsrl(MSR_K7_EVNTSEL3, 0); + wrmsrl(MSR_K7_PERFCTR3, pmc3); + wrmsrl(MSR_K7_EVNTSEL3, evntsel3); + } else { + release_perfctr_nmi(MSR_K7_PERFCTR0 + i); + release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); + } + + return pmc_now * tsc_khz / (tsc_now - tsc_start); +} +#endif + /* Duplicate of time_init() below, with hpet_enable part added */ void __init hpet_time_init(void) { diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c deleted file mode 100644 index e3d49c5..0000000 --- a/arch/x86/kernel/time_64.c +++ /dev/null @@ -1,126 +0,0 @@ -/* - * "High Precision Event Timer" based timekeeping. - * - * Copyright (c) 1991,1992,1995 Linus Torvalds - * Copyright (c) 1994 Alan Modra - * Copyright (c) 1995 Markus Kuhn - * Copyright (c) 1996 Ingo Molnar - * Copyright (c) 1998 Andrea Arcangeli - * Copyright (c) 2002,2006 Vojtech Pavlik - * Copyright (c) 2003 Andi Kleen - * RTC support code taken from arch/i386/kernel/timers/time_hpet.c - */ - -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include - -volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; - -unsigned long profile_pc(struct pt_regs *regs) -{ - unsigned long pc = instruction_pointer(regs); - - /* Assume the lock function has either no stack frame or a copy - of flags from PUSHF - Eflags always has bits 22 and up cleared unlike kernel addresses. */ - if (!user_mode(regs) && in_lock_functions(pc)) { - unsigned long *sp = (unsigned long *)regs->sp; - if (sp[0] >> 22) - return sp[0]; - if (sp[1] >> 22) - return sp[1]; - } - return pc; -} -EXPORT_SYMBOL(profile_pc); - -static irqreturn_t timer_event_interrupt(int irq, void *dev_id) -{ - add_pda(irq0_irqs, 1); - - global_clock_event->event_handler(global_clock_event); - - return IRQ_HANDLED; -} - -/* calibrate_cpu is used on systems with fixed rate TSCs to determine - * processor frequency */ -#define TICK_COUNT 100000000 -unsigned long __init calibrate_cpu(void) -{ - int tsc_start, tsc_now; - int i, no_ctr_free; - unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0; - unsigned long flags; - - for (i = 0; i < 4; i++) - if (avail_to_resrv_perfctr_nmi_bit(i)) - break; - no_ctr_free = (i == 4); - if (no_ctr_free) { - i = 3; - rdmsrl(MSR_K7_EVNTSEL3, evntsel3); - wrmsrl(MSR_K7_EVNTSEL3, 0); - rdmsrl(MSR_K7_PERFCTR3, pmc3); - } else { - reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i); - reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } - local_irq_save(flags); - /* start measuring cycles, incrementing from 0 */ - wrmsrl(MSR_K7_PERFCTR0 + i, 0); - wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76); - rdtscl(tsc_start); - do { - rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now); - tsc_now = get_cycles(); - } while ((tsc_now - tsc_start) < TICK_COUNT); - - local_irq_restore(flags); - if (no_ctr_free) { - wrmsrl(MSR_K7_EVNTSEL3, 0); - wrmsrl(MSR_K7_PERFCTR3, pmc3); - wrmsrl(MSR_K7_EVNTSEL3, evntsel3); - } else { - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } - - return pmc_now * tsc_khz / (tsc_now - tsc_start); -} - -static struct irqaction irq0 = { - .handler = timer_event_interrupt, - .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING, - .mask = CPU_MASK_NONE, - .name = "timer" -}; - -void __init hpet_time_init(void) -{ - if (!hpet_enable()) - setup_pit_timer(); - - setup_irq(0, &irq0); -} - -void __init time_init(void) -{ - tsc_init(); - if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP)) - vgetcpu_mode = VGETCPU_RDTSCP; - else - vgetcpu_mode = VGETCPU_LSL; - - late_time_init = choose_time_init(); -} diff --git a/include/asm-x86/segment.h b/include/asm-x86/segment.h index ea5f0a8..5d6e694 100644 --- a/include/asm-x86/segment.h +++ b/include/asm-x86/segment.h @@ -131,12 +131,6 @@ * Matching rules for certain types of segments. */ -/* Matches only __KERNEL_CS, ignoring PnP / USER / APM segments */ -#define SEGMENT_IS_KERNEL_CODE(x) (((x) & 0xfc) == GDT_ENTRY_KERNEL_CS * 8) - -/* Matches __KERNEL_CS and __USER_CS (they must be 2 entries apart) */ -#define SEGMENT_IS_FLAT_CODE(x) (((x) & 0xec) == GDT_ENTRY_KERNEL_CS * 8) - /* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */ #define SEGMENT_IS_PNP_CODE(x) (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8) diff --git a/include/asm-x86/timer.h b/include/asm-x86/timer.h index d0babce..013b2b8 100644 --- a/include/asm-x86/timer.h +++ b/include/asm-x86/timer.h @@ -10,10 +10,10 @@ unsigned long long native_sched_clock(void); unsigned long native_calibrate_tsc(void); #ifdef CONFIG_X86_32 -extern int timer_ack; extern int recalibrate_cpu_khz(void); #endif /* CONFIG_X86_32 */ +extern int timer_ack; extern int no_timer_check; #ifndef CONFIG_PARAVIRT -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/