[PATCH] x86/apbt: Moorestown APB system timer driver
From: Jacob Pan
Date: Wed Jul 15 2009 - 17:12:55 EST
Moorestown platform has introduced legacy replacement system timers, called
APB timers. There are four timers available to the kernel via SFI MTMR table.
APB timers are always running and have a known frequency. Two timers used
for per CPU clockevent deivces, one for clocksource, one by the watchdog
driver.
This driver serve similar functionality found in i8254 and HPET,
APB timers are given higher rating than local APIC timer so that they are
used for per CPU timer in SMP/HT. Broadcast timer is avoided. If cmdline
option no_percpu_apbt is given, the kernel will pick local APIC timers
and one APB timer as broadcast clockevent device.
Signed-off-by: Jacob Pan <jacob.jun.pan@xxxxxxxxx>
---
Documentation/kernel-parameters.txt | 4 +
arch/x86/Kconfig | 11 +
arch/x86/include/asm/apb_timer.h | 67 +++
arch/x86/kernel/Makefile | 2 +-
arch/x86/kernel/apb_timer.c | 762 +++++++++++++++++++++++++++++++++++
arch/x86/kernel/apic/apic.c | 3 +
6 files changed, 848 insertions(+), 1 deletions(-)
create mode 100644 arch/x86/include/asm/apb_timer.h
create mode 100644 arch/x86/kernel/apb_timer.c
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 2b79f24..a58cbf6 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1654,6 +1654,10 @@ and is between 256 and 4096 characters. It is defined in the file
nomfgpt [X86-32] Disable Multi-Function General Purpose
Timer usage (for AMD Geode machines).
+ no_percpu_apbt [X86-32,APBT]
+ Disable per CPU APB timer as clockevent devices. this
+ will make the local APIC timer used as per CPU timer.
+
norandmaps Don't use address space randomization. Equivalent to
echo 0 > /proc/sys/kernel/randomize_va_space
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 95de8c0..6fa83a6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -571,6 +571,16 @@ config HPET_EMULATE_RTC
def_bool y
depends on HPET_TIMER && (RTC=y || RTC=m || RTC_DRV_CMOS=m || RTC_DRV_CMOS=y)
+config APB_TIMER
+ def_bool y if MRST
+ prompt "Langwell APB Timer Support" if MRST
+ help
+ APB timer is the replacement for 8254, HPET on X86 MID platforms.
+ The APBT provides a stable time base on SMP
+ systems, unlike the TSC, but it is more expensive to access,
+ as it is off-chip. APB timers are always running regardless of CPU
+ C states, they are used as per CPU clockevent device when possible.
+
# Mark as embedded because too many people got it wrong.
# The code disables itself when not needed.
config DMI
@@ -1663,6 +1673,7 @@ config MRST
default n
depends on X86_32
select SFI
+ select APB_TIMER
help
Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin
Internet Device(MID) platform. Moorestown consists of two chips:
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
new file mode 100644
index 0000000..9a8596b
--- /dev/null
+++ b/arch/x86/include/asm/apb_timer.h
@@ -0,0 +1,67 @@
+/*
+ * apb_timer.h: Driver for Langwell APB timer based on Synopsis DesignWare
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Jacob Pan (jacob.jun.pan@xxxxxxxxx)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Note:
+ */
+
+#ifndef ASM_X86_APBT_H
+#define ASM_X86_APBT_H
+#include <linux/sfi.h>
+
+#ifdef CONFIG_APB_TIMER
+
+/* Langwell DW APB timer registers */
+#define APBTMR_N_LOAD_COUNT 0x00
+#define APBTMR_N_CURRENT_VALUE 0x04
+#define APBTMR_N_CONTROL 0x08
+#define APBTMR_N_EOI 0x0c
+#define APBTMR_N_INT_STATUS 0x10
+
+#define APBTMRS_INT_STATUS 0xa0
+#define APBTMRS_EOI 0xa4
+#define APBTMRS_RAW_INT_STATUS 0xa8
+#define APBTMRS_COMP_VERSION 0xac
+#define APBTMRS_REG_SIZE 0x14
+
+/* register bits */
+#define APBTMR_CONTROL_ENABLE (1<<0)
+#define APBTMR_CONTROL_MODE_PERIODIC (1<<1) /*1: periodic 0:free running */
+#define APBTMR_CONTROL_INT (1<<2)
+
+/* default memory mapped register base */
+#define LNW_SCU_ADDR 0xFF100000
+#define LNW_EXT_TIMER_OFFSET 0x1B800
+#define APBT_DEFAULT_BASE (LNW_SCU_ADDR+LNW_EXT_TIMER_OFFSET)
+#define LNW_EXT_TIMER_PGOFFSET 0x800
+
+/* APBT clock speed range from PCLK to fabric base, 25-100MHz */
+#define APBT_MAX_FREQ 50
+#define APBT_MIN_FREQ 1
+#define APBT_MMAP_SIZE 1024
+
+#define APBT_DEV_USED 1
+
+extern void apbt_time_init(void);
+extern struct clock_event_device *global_clock_event;
+extern struct sfi_mtimer_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM];
+extern unsigned long apbt_quick_calibrate(void);
+extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
+extern void apbt_setup_secondary_clock(void);
+extern unsigned int boot_cpu_id;
+extern int disable_apbt_percpu;
+
+#else /* CONFIG_APB_TIMER */
+
+static inline unsigned long apbt_quick_calibrate(void) {return 0; }
+static inline void apbt_time_init(void) {return 0; }
+
+#endif
+#endif /* ASM_X86_APBT_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f23811d..d1dcfb7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -87,7 +87,7 @@ obj-$(CONFIG_VM86) += vm86_32.o
obj-$(CONFIG_EARLY_PRINTK) += early_printk.o
obj-$(CONFIG_HPET_TIMER) += hpet.o
-
+obj-$(CONFIG_APB_TIMER) += apb_timer.o
obj-$(CONFIG_K8_NB) += k8.o
obj-$(CONFIG_MGEODE_LX) += geode_32.o mfgpt_32.o
obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
new file mode 100644
index 0000000..ad454ec
--- /dev/null
+++ b/arch/x86/kernel/apb_timer.c
@@ -0,0 +1,762 @@
+/*
+ * apb_timer.c: Driver for Langwell APB timers
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Jacob Pan (jacob.jun.pan@xxxxxxxxx)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Note:
+ * Langwell is the south complex of Intel Moorestown MID platform. There are
+ * eight external timers in total that can be used by the operating system.
+ * The timer information, such as frequency and addresses, is provided to the
+ * OS via SFI tables.
+ * Timer interrupts are routed via FW/HW emulated IOAPIC independently via
+ * individual redirection table entries (RTE).
+ * Unlike HPET, there is no master counter, therefore one of the timers are
+ * used as clocksource. The overall allocation looks like:
+ * - timer 0 - NR_CPUs for per cpu timer
+ * - one timer for clocksource
+ * - one timer for watchdog driver.
+ * It is also worth notice that APB timer does not support true one-shot mode,
+ * free-running mode will be used here to emulate one-shot mode.
+ * APB timer can also be used as broadcast timer along with per cpu local APIC
+ * timer, but by default APB timer has higher rating than local APIC timers.
+ */
+
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/sysdev.h>
+#include <linux/pm.h>
+#include <linux/pci.h>
+#include <linux/sfi.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/irq.h>
+
+#include <asm/fixmap.h>
+#include <asm/apb_timer.h>
+
+#define APBT_MASK CLOCKSOURCE_MASK(32)
+#define APBT_SHIFT 22
+#define APBT_CLOCKEVENT_RATING 150
+#define APBT_CLOCKSOURCE_RATING 250
+#define APBT_MIN_DELTA_USEC 200
+
+#define EVT_TO_APBT_DEV(evt) container_of(evt, struct apbt_dev, evt)
+#define APBT_CLOCKEVENT0_NUM (0)
+#define APBT_CLOCKEVENT1_NUM (1)
+#define APBT_CLOCKSOURCE_NUM (2)
+
+static unsigned long apbt_address;
+static int apb_timer_block_enabled;
+static void __iomem *apbt_virt_address;
+static int phy_cs_timer_id;
+
+/*
+ * Common DW APB timer info
+ */
+static uint64_t apbt_freq;
+
+static void apbt_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *evt);
+static int apbt_next_event(unsigned long delta,
+ struct clock_event_device *evt);
+static cycle_t apbt_read_clocksource(struct clocksource *cs);
+static void apbt_restart_clocksource(void);
+
+struct apbt_dev {
+ struct clock_event_device evt;
+ unsigned int num;
+ int cpu;
+ unsigned int irq;
+ unsigned int tick;
+ unsigned int count;
+ unsigned int flags;
+ char name[10];
+};
+
+int disable_apbt_percpu __cpuinitdata;
+
+#ifdef CONFIG_SMP
+static unsigned int apbt_num_timers_used;
+static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev);
+static struct apbt_dev *apbt_devs;
+#endif
+
+static inline unsigned long apbt_readl_reg(unsigned long a)
+{
+ return readl(apbt_virt_address + a);
+}
+
+static inline void apbt_writel_reg(unsigned long d, unsigned long a)
+{
+ writel(d, apbt_virt_address + a);
+}
+
+static inline unsigned long apbt_readl(int n, unsigned long a)
+{
+ return readl(apbt_virt_address + a + n * APBTMRS_REG_SIZE);
+}
+
+static inline void apbt_writel(int n, unsigned long d, unsigned long a)
+{
+ writel(d, apbt_virt_address + a + n * APBTMRS_REG_SIZE);
+}
+
+static inline void apbt_set_mapping(void)
+{
+ struct sfi_mtimer_entry *mtmr;
+
+ if (apbt_virt_address) {
+ pr_debug("APBT base already mapped\n");
+ return;
+ }
+ mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
+ if (mtmr == NULL) {
+ printk(KERN_ERR "Failed to get MTMR %d from SFI\n",
+ APBT_CLOCKEVENT0_NUM);
+ return;
+ }
+ apbt_address = (unsigned long)mtmr->phy_addr;
+ if (!apbt_address) {
+ printk(KERN_WARNING "No timer base from SFI, use default\n");
+ apbt_address = APBT_DEFAULT_BASE;
+ }
+ apbt_virt_address = ioremap_nocache(apbt_address, APBT_MMAP_SIZE);
+ if (apbt_virt_address) {
+ pr_debug("Mapped APBT physical addr %p at virtual addr %p\n",\
+ (void *)apbt_address, (void *)apbt_virt_address);
+ } else {
+ pr_debug("Failed mapping APBT phy address at %p\n",\
+ (void *)apbt_address);
+ goto panic_noapbt;
+ }
+ apbt_freq = mtmr->freq / USEC_PER_SEC;
+ sfi_free_mtmr(mtmr);
+
+ /* Now figure out the physical timer id for clocksource device */
+ mtmr = sfi_get_mtmr(APBT_CLOCKSOURCE_NUM);
+ if (mtmr == NULL)
+ goto panic_noapbt;
+
+ /* Now figure out the physical timer id */
+ phy_cs_timer_id = (unsigned int)(mtmr->phy_addr & 0xff)
+ / APBTMRS_REG_SIZE;
+ pr_debug("Use timer %d for clocksource\n", phy_cs_timer_id);
+ return;
+
+panic_noapbt:
+ panic("Failed to setup APB system timer\n");
+
+}
+
+static inline void apbt_clear_mapping(void)
+{
+ iounmap(apbt_virt_address);
+ apbt_virt_address = NULL;
+}
+
+/*
+ * APBT timer interrupt enable / disable
+ */
+static inline int is_apbt_capable(void)
+{
+ return apbt_virt_address ? 1 : 0;
+}
+
+static struct clocksource clocksource_apbt = {
+ .name = "apbt",
+ .rating = APBT_CLOCKSOURCE_RATING,
+ .read = apbt_read_clocksource,
+ .mask = APBT_MASK,
+ .shift = APBT_SHIFT,
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+ .resume = apbt_restart_clocksource,
+};
+
+/* boot APB clock event device */
+static struct clock_event_device apbt_clockevent = {
+ .name = "apbt0",
+ .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+ .set_mode = apbt_set_mode,
+ .set_next_event = apbt_next_event,
+ .shift = APBT_SHIFT,
+ .irq = 0,
+ .rating = APBT_CLOCKEVENT_RATING,
+};
+
+/*
+ * if user does not want to use per CPU apb timer, just give it a lower rating
+ * than local apic timer and skip the late per cpu timer init.
+ */
+static inline int __init setup_no_percpu_apbt(char *arg)
+{
+ disable_apbt_percpu = 1;
+ return 0;
+}
+__setup("no_percpu_apbt", setup_no_percpu_apbt);
+
+/*
+ * start count down from 0xffff_ffff. this is done by toggling the enable bit
+ * then load initial load count to ~0.
+ */
+static void apbt_start_counter(int n)
+{
+ unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
+
+ ctrl &= ~APBTMR_CONTROL_ENABLE;
+ apbt_writel(n, ctrl, APBTMR_N_CONTROL);
+ apbt_writel(n, ~0, APBTMR_N_LOAD_COUNT);
+ /* enable, mask interrupt */
+ ctrl &= ~APBTMR_CONTROL_MODE_PERIODIC;
+ ctrl |= (APBTMR_CONTROL_ENABLE | APBTMR_CONTROL_INT);
+ apbt_writel(n, ctrl, APBTMR_N_CONTROL);
+ /* read it once to get cached counter value initialized */
+ apbt_read_clocksource(&clocksource_apbt);
+}
+
+#ifdef CONFIG_SMP
+static irqreturn_t apbt_interrupt_handler(int irq, void *data)
+{
+ struct apbt_dev *dev = (struct apbt_dev *)data;
+ struct clock_event_device *aevt = &dev->evt;
+
+ if (!aevt->event_handler) {
+ printk(KERN_INFO "Spurious APBT timer interrupt on %d\n",
+ dev->num);
+ return IRQ_NONE;
+ }
+ aevt->event_handler(aevt);
+ return IRQ_HANDLED;
+}
+#endif
+
+static void apbt_restart_clocksource(void)
+{
+ apbt_start_counter(phy_cs_timer_id);
+}
+
+/* Setup IRQ routing via IOAPIC */
+#ifdef CONFIG_SMP
+static void apbt_setup_irq(struct apbt_dev *adev)
+{
+ struct irq_chip *chip;
+
+ /* timer0 irq has been setup early */
+ if (adev->irq == 0)
+ return;
+ chip = get_irq_chip(adev->irq);
+ disable_irq(adev->irq);
+ irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
+ /* APB timer irqs are set up as mp_irqs, timer is edge triggerred */
+ set_irq_chip_and_handler_name(adev->irq, chip, handle_edge_irq, "edge");
+ enable_irq(adev->irq);
+ if (system_state == SYSTEM_BOOTING)
+ if (request_irq(adev->irq, apbt_interrupt_handler,
+ IRQF_DISABLED|IRQF_NOBALANCING, adev->name, adev)) {
+ printk(KERN_ERR "Failed request IRQ for APBT%d\n", adev->num);
+ }
+}
+#endif
+
+static void apbt_enable_int(int n)
+{
+ unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
+ /* clear pending intr */
+ apbt_readl(n, APBTMR_N_EOI);
+ ctrl &= ~APBTMR_CONTROL_INT;
+ apbt_writel(n, ctrl, APBTMR_N_CONTROL);
+}
+
+static void apbt_disable_int(int n)
+{
+ unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
+
+ ctrl &= ~APBTMR_CONTROL_INT;
+ ctrl |= APBTMR_CONTROL_INT;
+ apbt_writel(n, ctrl, APBTMR_N_CONTROL);
+}
+
+
+static int apbt_clockevent_register(void)
+{
+ struct sfi_mtimer_entry *mtmr;
+
+ mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
+ if (mtmr == NULL) {
+ printk(KERN_ERR "Failed to get MTMR %d from SFI\n",
+ APBT_CLOCKEVENT0_NUM);
+ return -ENODEV;
+ }
+
+ /*
+ * We need to calculate the scaled math multiplication factor for
+ * nanosecond to apbt tick conversion.
+ * mult = (nsec/cycle)*2^APBT_SHIFT
+ */
+ apbt_clockevent.mult = div_sc((unsigned long) mtmr->freq
+ , NSEC_PER_SEC, APBT_SHIFT);
+
+ /* Calculate the min / max delta */
+ apbt_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
+ &apbt_clockevent);
+ apbt_clockevent.min_delta_ns = clockevent_delta2ns(
+ APBT_MIN_DELTA_USEC*apbt_freq,
+ &apbt_clockevent);
+ /*
+ * Start apbt with the boot cpu mask and make it
+ * global if not used for per cpu timer.
+ */
+ apbt_clockevent.cpumask = cpumask_of(smp_processor_id());
+
+ if (disable_apbt_percpu) {
+ apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100;
+ global_clock_event = &apbt_clockevent;
+ printk(KERN_DEBUG "%s clockevent registered as global\n",
+ global_clock_event->name);
+ }
+ if (request_irq(apbt_clockevent.irq, apbt_interrupt_handler,
+ IRQF_DISABLED|IRQF_NOBALANCING,
+ apbt_clockevent.name, &apbt_clockevent)) {
+ printk(KERN_ERR "Failed request IRQ for APBT%d\n",
+ apbt_clockevent.irq);
+ }
+
+ clockevents_register_device(&apbt_clockevent);
+ /* Start APBT 0 interrupts */
+ apbt_enable_int(APBT_CLOCKEVENT0_NUM);
+
+ sfi_free_mtmr(mtmr);
+ return 0;
+}
+
+#ifdef CONFIG_SMP
+/* Should be called with per cpu */
+static int apbt_clockevent_late_register(void)
+{
+ struct apbt_dev *adev;
+ struct clock_event_device *aevt;
+ int cpu;
+
+ /* Don't register boot CPU clockevent */
+ cpu = smp_processor_id();
+ if (cpu == boot_cpu_id)
+ return 0;
+ /*
+ * We need to calculate the scaled math multiplication factor for
+ * nanosecond to apbt tick conversion.
+ * mult = (nsec/cycle)*2^APBT_SHIFT
+ */
+ printk(KERN_INFO "Init per CPU clockevent %d\n", cpu);
+ adev = &per_cpu(cpu_apbt_dev, cpu);
+ aevt = &adev->evt;
+
+ memcpy(aevt, &apbt_clockevent, sizeof(*aevt));
+ aevt->cpumask = cpumask_of(cpu);
+ aevt->name = adev->name;
+ aevt->mode = CLOCK_EVT_MODE_UNUSED;
+
+ printk(KERN_INFO "Registering CPU %d clockevent device %s, mask %08x\n",
+ cpu, aevt->name, *(u32 *)aevt->cpumask);
+
+ apbt_setup_irq(adev);
+
+ clockevents_register_device(aevt);
+
+ apbt_enable_int(cpu);
+
+ return 0;
+}
+
+/* Initialize per CPU timer data structures based on SFI MTMR table */
+static int apbt_cpuhp_notify(struct notifier_block *n,
+ unsigned long action, void *hcpu)
+{
+ unsigned long cpu = (unsigned long)hcpu;
+ struct apbt_dev *adev = &per_cpu(cpu_apbt_dev, cpu);
+
+ switch (action & 0xf) {
+ case CPU_DEAD:
+ if (system_state == SYSTEM_RUNNING)
+ pr_debug("skipping APBT CPU %lu offline\n", cpu);
+ else if (adev) {
+ pr_debug("APBT clockevent for cpu %lu offline\n", cpu);
+ apbt_disable_int(cpu);
+ free_irq(adev->irq, adev);
+ }
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static __init int apbt_late_init(void)
+{
+ if (disable_apbt_percpu)
+ return 0;
+ /* This notifier should be called after workqueue is ready */
+ hotcpu_notifier(apbt_cpuhp_notify, -20);
+ return 0;
+}
+fs_initcall(apbt_late_init);
+
+inline void apbt_setup_secondary_clock(void)
+{
+
+ apbt_clockevent_late_register();
+}
+
+#endif
+
+static void apbt_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *evt)
+{
+ unsigned long ctrl;
+ uint64_t delta;
+ int timer_num;
+ struct apbt_dev *adev = EVT_TO_APBT_DEV(evt);
+
+ timer_num = adev->num;
+
+ if ((timer_num < 0) || (timer_num > sfi_mtimer_num)) {
+ printk(KERN_ERR "apbt: set mode for invalid timer %d\n",
+ timer_num);
+ return;
+ }
+ pr_debug("%s CPU %d timer %d mode=%d\n",
+ __func__, first_cpu(*evt->cpumask), timer_num, mode);
+
+ switch (mode) {
+ case CLOCK_EVT_MODE_PERIODIC:
+ delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * apbt_clockevent.mult;
+ delta >>= apbt_clockevent.shift;
+ ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL);
+ ctrl |= APBTMR_CONTROL_MODE_PERIODIC;
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+ /*
+ * DW APB p. 46, have to disable timer before load counter,
+ * may cause sync problem.
+ */
+ ctrl &= ~APBTMR_CONTROL_ENABLE;
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+ udelay(1);
+ pr_debug("Setting clock period %d for HZ %d\n", (int)delta, HZ);
+ apbt_writel(timer_num, delta, APBTMR_N_LOAD_COUNT);
+ ctrl |= APBTMR_CONTROL_ENABLE;
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+ break;
+ /* APB timer does not have one-shot mode, use free running mode */
+ case CLOCK_EVT_MODE_ONESHOT:
+ ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL);
+ /*
+ * set free running mode, this mode will let timer reload max
+ * timeout which will give time (3min on 25MHz clock) to rearm
+ * the next event, therefore emulate the one-shot mode.
+ */
+ ctrl &= ~APBTMR_CONTROL_ENABLE;
+ ctrl &= ~APBTMR_CONTROL_MODE_PERIODIC;
+
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+ /* write again to set free running mode */
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+
+ /*
+ * DW APB p. 46, load counter with all 1s before starting free
+ * running mode.
+ */
+ apbt_writel(timer_num, ~0, APBTMR_N_LOAD_COUNT);
+ ctrl |= APBTMR_CONTROL_ENABLE;
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+ break;
+
+ case CLOCK_EVT_MODE_UNUSED:
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL);
+ ctrl &= ~APBTMR_CONTROL_ENABLE;
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+ break;
+
+ case CLOCK_EVT_MODE_RESUME:
+ apbt_enable_int(timer_num);
+ break;
+ }
+}
+
+static int apbt_next_event(unsigned long delta,
+ struct clock_event_device *evt)
+{
+ unsigned long ctrl;
+ int timer_num;
+
+ struct apbt_dev *adev = EVT_TO_APBT_DEV(evt);
+
+ timer_num = adev->num;
+ /* Disable timer */
+ ctrl = apbt_readl(timer_num, APBTMR_N_CONTROL);
+ ctrl &= ~APBTMR_CONTROL_ENABLE;
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+ /* write new count */
+ apbt_writel(timer_num, delta, APBTMR_N_LOAD_COUNT);
+ ctrl |= APBTMR_CONTROL_ENABLE;
+ apbt_writel(timer_num, ctrl, APBTMR_N_CONTROL);
+ return 0;
+}
+
+/*
+ * APB timer clock is not in sync with pclk on Langwell, which translates to
+ * unreliable read value caused by sampling error. the error does not add up
+ * overtime and only happens when sampling a 0 as a 1 by mistake. so the time
+ * would go backwards. the following code is trying to prevent time traveling
+ * backwards. little bit paranoid.
+ */
+static cycle_t apbt_read_clocksource(struct clocksource *cs)
+{
+ unsigned long t0, t1, t2;
+ static unsigned long last_read;
+
+bad_count:
+ t1 = apbt_readl(phy_cs_timer_id,
+ APBTMR_N_CURRENT_VALUE);
+ t2 = apbt_readl(phy_cs_timer_id,
+ APBTMR_N_CURRENT_VALUE);
+ if (unlikely(t1 < t2)) {
+ pr_debug("APBT: read current count error %lx:%lx:%lx\n",
+ t1, t2, t2 - t1);
+ goto bad_count;
+ }
+ /*
+ * check against cached last read, makes sure time does not go back.
+ * it could be a normal rollover but we will do tripple check anyway
+ */
+ if (unlikely(t2 > last_read)) {
+ /* check if we have a normal rollover */
+ unsigned long raw_intr_status =
+ apbt_readl_reg(APBTMRS_RAW_INT_STATUS);
+ /*
+ * cs timer interrupt is masked but raw intr bit is set if
+ * rollover occurs. then we read EOI reg to clear it.
+ */
+ if (raw_intr_status & (1 << phy_cs_timer_id)) {
+ apbt_readl(phy_cs_timer_id, APBTMR_N_EOI);
+ goto out;
+ }
+ pr_debug("APB CS going back %lx:%lx:%lx ",
+ t2, last_read, t2 - last_read);
+bad_count_x3:
+ pr_debug(KERN_INFO "tripple check enforced\n");
+ t0 = apbt_readl(phy_cs_timer_id,
+ APBTMR_N_CURRENT_VALUE);
+ udelay(1);
+ t1 = apbt_readl(phy_cs_timer_id,
+ APBTMR_N_CURRENT_VALUE);
+ udelay(1);
+ t2 = apbt_readl(phy_cs_timer_id,
+ APBTMR_N_CURRENT_VALUE);
+ if ((t2 > t1) || (t1 > t0)) {
+ printk(KERN_ERR "Error: APB CS tripple check failed\n");
+ goto bad_count_x3;
+ }
+ }
+out:
+ last_read = t2;
+ return (cycle_t)~t2;
+}
+
+static int apbt_clocksource_register(void)
+{
+ u64 start, now;
+ cycle_t t1;
+
+ /* Start the counter, use timer 2 as source, timer 0/1 for event */
+ apbt_start_counter(phy_cs_timer_id);
+
+ /* Verify whether apbt counter works */
+ t1 = apbt_read_clocksource(&clocksource_apbt);
+ rdtscll(start);
+
+ /*
+ * We don't know the TSC frequency yet, but waiting for
+ * 200000 TSC cycles is safe:
+ * 4 GHz == 50us
+ * 1 GHz == 200us
+ */
+ do {
+ rep_nop();
+ rdtscll(now);
+ } while ((now - start) < 200000UL);
+
+ /* APBT is the only always on clocksource, it has to work! */
+ if (t1 == apbt_read_clocksource(&clocksource_apbt))
+ panic("APBT counter not counting. APBT disabled\n");
+
+ /*
+ * initialize and register APBT clocksource
+ * convert that to ns/clock cycle
+ * mult = (ns/c) * 2^APBT_SHIFT
+ */
+ clocksource_apbt.mult = div_sc(MSEC_PER_SEC,
+ (unsigned long) apbt_freq, APBT_SHIFT);
+ clocksource_register(&clocksource_apbt);
+
+ return 0;
+}
+
+/*
+ * Early setup the APBT timer, only use timer 0 for booting then switch to
+ * per CPU timer if possible.
+ * returns 1 if per cpu apbt is setup
+ * returns 0 if no per cpu apbt is chosen
+ * panic if set up failed, this is the only platform timer on Moorestown.
+ */
+void __init apbt_time_init(void)
+{
+#ifdef CONFIG_SMP
+ int i;
+ struct sfi_mtimer_entry *p_mtmr;
+ unsigned int percpu_timer;
+ struct apbt_dev *adev;
+#endif
+
+ if (apb_timer_block_enabled)
+ return;
+ apbt_set_mapping();
+ if (apbt_virt_address) {
+ pr_debug("Found APBT version 0x%lx\n",\
+ apbt_readl_reg(APBTMRS_COMP_VERSION));
+ } else
+ goto out_noapbt;
+ /*
+ * Read the frequency and check for a sane value, for ESL model
+ * we extend the possible clock range to allow time scaling.
+ */
+
+ if (apbt_freq < APBT_MIN_FREQ || apbt_freq > APBT_MAX_FREQ) {
+ pr_debug("APBT has invalid freq 0x%llx\n", apbt_freq);
+ goto out_noapbt;
+ }
+ if (apbt_clocksource_register()) {
+ pr_debug("APBT has failed to register clocksource\n");
+ goto out_noapbt;
+ }
+ if (!apbt_clockevent_register())
+ apb_timer_block_enabled = 1;
+ else {
+ pr_debug("APBT has failed to register clockevent\n");
+ goto out_noapbt;
+ }
+#ifdef CONFIG_SMP
+ /* kernel cmdline disable apb timer, so we will use lapic timers */
+ if (disable_apbt_percpu) {
+ printk(KERN_INFO "apbt: disabled per cpu timer\n");
+ return;
+ }
+ pr_debug("%s: %d CPUs online\n", __func__, num_online_cpus());
+ if (num_possible_cpus() <= 2 &&
+ num_possible_cpus() <= sfi_mtimer_num) {
+ percpu_timer = 1;
+ apbt_num_timers_used = num_possible_cpus();
+ } else {
+ percpu_timer = 0;
+ apbt_num_timers_used = 1;
+ adev = &per_cpu(cpu_apbt_dev, 0);
+ adev->flags &= ~APBT_DEV_USED;
+ }
+ pr_debug("%s: %d APB timers used\n", __func__, apbt_num_timers_used);
+
+ /* here we set up per CPU timer data structure */
+ apbt_devs = kzalloc(sizeof(struct apbt_dev) * apbt_num_timers_used,
+ GFP_KERNEL);
+ if (!apbt_devs) {
+ printk(KERN_ERR "Failed to allocate APB timer devices\n");
+ return;
+ }
+ for (i = 0; i < apbt_num_timers_used; i++) {
+ adev = &per_cpu(cpu_apbt_dev, i);
+ adev->num = i;
+ adev->cpu = i;
+ p_mtmr = sfi_get_mtmr(i);
+ if (p_mtmr) {
+ adev->tick = p_mtmr->freq;
+ adev->irq = p_mtmr->irq;
+ } else
+ printk(KERN_ERR "Failed to get timer for cpu %d\n", i);
+ adev->count = 0;
+ sprintf(adev->name, "apbt%d", i);
+ }
+#endif
+
+ return;
+
+out_noapbt:
+ apbt_clear_mapping();
+ apb_timer_block_enabled = 0;
+ panic("failed to enable APB timer\n");
+}
+
+static inline void apbt_disable(int n)
+{
+ if (is_apbt_capable()) {
+ unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
+ ctrl &= ~APBTMR_CONTROL_ENABLE;
+ apbt_writel(n, ctrl, APBTMR_N_CONTROL);
+ }
+}
+
+/* called before apb_timer_enable, use early map */
+unsigned long apbt_quick_calibrate()
+{
+ int i, scale;
+ u64 old, new;
+ cycle_t t1, t2;
+ unsigned long khz = 0;
+ u32 loop, shift;
+
+ apbt_set_mapping();
+ apbt_start_counter(phy_cs_timer_id);
+
+ /* check if the timer can count down, otherwise return */
+ old = apbt_read_clocksource(&clocksource_apbt);
+ i = 10000;
+ while (--i) {
+ if (old != apbt_read_clocksource(&clocksource_apbt))
+ break;
+ }
+ if (!i)
+ goto failed;
+
+ /* count 16 ms */
+ loop = (apbt_freq * 1000) << 4;
+
+ /* restart the timer to ensure it won't get to 0 in the calibration */
+ apbt_start_counter(phy_cs_timer_id);
+
+ old = apbt_read_clocksource(&clocksource_apbt);
+ old += loop;
+
+ t1 = __native_read_tsc();
+
+ do {
+ new = apbt_read_clocksource(&clocksource_apbt);
+ } while (new < old);
+
+ t2 = __native_read_tsc();
+
+ shift = 5;
+ if (unlikely(loop >> shift == 0)) {
+ printk(KERN_INFO
+ "APBT TSC calibration failed, not enough resolution\n");
+ return 0;
+ }
+ scale = (int)div_u64((t2 - t1), loop >> shift);
+ khz = (scale * apbt_freq * 1000) >> shift;
+ printk(KERN_INFO "TSC freq calculated by APB timer is %lu khz\n", khz);
+ return khz;
+failed:
+ return 0;
+}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index c4eabd4..4503767 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -738,6 +738,9 @@ static int __init calibrate_APIC_clock(void)
*/
void __init setup_boot_APIC_clock(void)
{
+ /* we rely on global clockevent for calibration */
+ if (global_clock_event == NULL)
+ return;
/*
* The local apic timer can be disabled via the kernel
* commandline or from the CPU detection code. Register the lapic
--
1.5.6.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/