select HAVE_OPROFILE
select HAVE_KPROBES if (!XIP_KERNEL)
select HAVE_KRETPROBES if (HAVE_KPROBES)
+ select HAVE_FTRACE if (!XIP_KERNEL)
+ select HAVE_DYNAMIC_FTRACE if (HAVE_FTRACE)
help
The ARM series is a line of low-power-consumption RISC chip designs
licensed by ARM Ltd and targeted at embedded applications and
Europe. There is an ARM Linux project with a web page at
<http://www.arm.linux.org.uk/>.
+config HAVE_PWM
+ bool
+
config SYS_SUPPORTS_APM_EMULATION
bool
bool
default y
+config HAVE_LATENCYTOP_SUPPORT
+ bool
+ depends on !SMP
+ default y
+
config LOCKDEP_SUPPORT
bool
default y
config ARCH_MTD_XIP
bool
+config GENERIC_HARDIRQS_NO__DO_IRQ
+ bool
+ def_bool y
+
if OPROFILE
config OPROFILE_ARMV6
help
Support for Cirrus Logic 711x/721x based boards.
-config ARCH_CO285
- bool "Co-EBSA285"
- select FOOTBRIDGE
- select FOOTBRIDGE_ADDIN
- help
- Support for Intel's EBSA285 companion chip.
-
config ARCH_EBSA110
bool "EBSA-110"
select ISA
depends on MMU
select PLAT_IOP
select PCI
+ select GENERIC_GPIO
+ select HAVE_GPIO_LIB
help
Support for Intel's 80219 and IOP32X (XScale) family of
processors.
depends on MMU
select PLAT_IOP
select PCI
+ select GENERIC_GPIO
+ select HAVE_GPIO_LIB
help
Support for Intel's IOP33X (XScale) family of processors.
If you have any questions or comments about the Linux kernel port
to this board, send e-mail to <sjhill@cotw.com>.
+config ARCH_KIRKWOOD
+ bool "Marvell Kirkwood"
+ select PCI
+ select GENERIC_TIME
+ select GENERIC_CLOCKEVENTS
+ select PLAT_ORION
+ help
+ Support for the following Marvell Kirkwood series SoCs:
+ 88F6180, 88F6192 and 88F6281.
+
config ARCH_KS8695
bool "Micrel/Kendin KS8695"
select GENERIC_GPIO
<http://www.digi.com/products/microprocessors/index.jsp>
+config ARCH_LOKI
+ bool "Marvell Loki (88RC8480)"
+ select GENERIC_TIME
+ select GENERIC_CLOCKEVENTS
+ select PLAT_ORION
+ help
+ Support for the Marvell Loki (88RC8480) SoC.
+
+config ARCH_MV78XX0
+ bool "Marvell MV78xx0"
+ select PCI
+ select GENERIC_TIME
+ select GENERIC_CLOCKEVENTS
+ select PLAT_ORION
+ help
+ Support for the following Marvell MV78xx0 series SoCs:
+ MV781x0, MV782x0.
+
config ARCH_MXC
bool "Freescale MXC/iMX-based"
+ select GENERIC_TIME
+ select GENERIC_CLOCKEVENTS
select ARCH_MTD_XIP
+ select GENERIC_GPIO
+ select HAVE_GPIO_LIB
help
Support for Freescale MXC/iMX-based family of processors
select PLAT_ORION
help
Support for the following Marvell Orion 5x series SoCs:
- Orion-1 (5181), Orion-NAS (5182), Orion-2 (5281.)
+ Orion-1 (5181), Orion-VoIP (5181L), Orion-NAS (5182),
+ Orion-2 (5281).
config ARCH_PNX4008
bool "Philips Nexperia PNX4008 Mobile"
select FIQ
select TIMER_ACORN
select ARCH_MAY_HAVE_PC_FDC
+ select HAVE_PATA_PLATFORM
select ISA_DMA_API
select NO_IOPORT
help
source "arch/arm/mach-ixp23xx/Kconfig"
+source "arch/arm/mach-loki/Kconfig"
+
+source "arch/arm/mach-mv78xx0/Kconfig"
+
source "arch/arm/mach-pxa/Kconfig"
source "arch/arm/mach-sa1100/Kconfig"
source "arch/arm/mach-orion5x/Kconfig"
+source "arch/arm/mach-kirkwood/Kconfig"
+
source "arch/arm/plat-s3c24xx/Kconfig"
source "arch/arm/plat-s3c/Kconfig"
config SMP
bool "Symmetric Multi-Processing (EXPERIMENTAL)"
depends on EXPERIMENTAL && (REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP)
+ select USE_GENERIC_SMP_HELPERS
help
This enables support for systems with more than one CPU. If you have
a system with only one CPU, like most personal computers, say N. If
Say Y here if you are building a kernel for a desktop, embedded
or real-time system. Say N if you are unsure.
-config NO_IDLE_HZ
- bool "Dynamic tick timer"
- depends on !GENERIC_CLOCKEVENTS
- help
- Select this option if you want to disable continuous timer ticks
- and have them programmed to occur as required. This option saves
- power as the system can remain in idle state for longer.
-
- By default dynamic tick is disabled during the boot, and can be
- manually enabled with:
-
- echo 1 > /sys/devices/system/timer/timer0/dyn_tick
-
- Alternatively, if you want dynamic tick automatically enabled
- during boot, pass "dyntick=enable" via the kernel command string.
-
- Please note that dynamic tick may affect the accuracy of
- timekeeping on some platforms depending on the implementation.
- Currently at least OMAP, PXA2xx and SA11x0 platforms are known
- to have accurate timekeeping with dynamic tick.
-
config HZ
int
default 128 if ARCH_L7200
config LEDS
bool "Timer and CPU usage LEDs"
- depends on ARCH_CDB89712 || ARCH_CO285 || ARCH_EBSA110 || \
+ depends on ARCH_CDB89712 || ARCH_EBSA110 || \
ARCH_EBSA285 || ARCH_IMX || ARCH_INTEGRATOR || \
ARCH_LUBBOCK || MACH_MAINSTONE || ARCH_NETWINDER || \
ARCH_OMAP || ARCH_P720T || ARCH_PXA_IDP || \
config MIPS_L1_CACHE_SHIFT
int
default "4" if MACH_DECSTATION
- default "7" if SGI_IP27 || SGI_IP28 || SNI_RM
+ default "7" if SGI_IP22 || SGI_IP27 || SGI_IP28 || SNI_RM
default "4" if PMC_MSP4200_EVAL
default "5"
bool "Multi-Processing support"
depends on SYS_SUPPORTS_SMP
select IRQ_PER_CPU
+ select USE_GENERIC_SMP_HELPERS
help
This enables support for systems with more than one CPU. If you have
a system with only one CPU, like most personal computers, say N. If
config PPC
bool
default y
+ select HAVE_DYNAMIC_FTRACE
+ select HAVE_FTRACE
select HAVE_IDE
- select HAVE_OPROFILE
select HAVE_KPROBES
select HAVE_KRETPROBES
select HAVE_LMB
+ select USE_GENERIC_SMP_HELPERS if SMP
+ select HAVE_OPROFILE
config EARLY_PRINTK
bool
* Exports appldata_register_ops() and appldata_unregister_ops() for the
* data gathering modules.
*
- * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH.
+ * Copyright IBM Corp. 2003, 2008
*
* Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
*/
*/
static void appldata_timer_function(unsigned long data)
{
- P_DEBUG(" -= Timer =-\n");
- P_DEBUG("CPU: %i, expire_count: %i\n", smp_processor_id(),
- atomic_read(&appldata_expire_count));
if (atomic_dec_and_test(&appldata_expire_count)) {
atomic_set(&appldata_expire_count, num_online_cpus());
queue_work(appldata_wq, (struct work_struct *) data);
struct appldata_ops *ops;
int i;
- P_DEBUG(" -= Work Queue =-\n");
i = 0;
get_online_cpus();
spin_lock(&appldata_ops_lock);
list_for_each(lh, &appldata_ops_list) {
ops = list_entry(lh, struct appldata_ops, list);
- P_DEBUG("list_for_each loop: %i) active = %u, name = %s\n",
- ++i, ops->active, ops->name);
if (ops->active == 1) {
ops->callback(ops->data);
}
per_cpu(appldata_timer, i).expires = per_cpu_interval;
smp_call_function_single(i, add_virt_timer_periodic,
&per_cpu(appldata_timer, i),
- 0, 1);
+ 1);
}
appldata_timer_active = 1;
- P_INFO("Monitoring timer started.\n");
break;
case APPLDATA_DEL_TIMER:
for_each_online_cpu(i)
break;
appldata_timer_active = 0;
atomic_set(&appldata_expire_count, num_online_cpus());
- P_INFO("Monitoring timer stopped.\n");
break;
case APPLDATA_MOD_TIMER:
per_cpu_interval = (u64) (appldata_interval*1000 /
args.timer = &per_cpu(appldata_timer, i);
args.expires = per_cpu_interval;
smp_call_function_single(i, __appldata_mod_vtimer_wrap,
- &args, 0, 1);
+ &args, 1);
}
}
}
}
interval = 0;
sscanf(buf, "%i", &interval);
- if (interval <= 0) {
- P_ERROR("Timer CPU interval has to be > 0!\n");
+ if (interval <= 0)
return -EINVAL;
- }
get_online_cpus();
spin_lock(&appldata_timer_lock);
__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
spin_unlock(&appldata_timer_lock);
put_online_cpus();
-
- P_INFO("Monitoring CPU interval set to %u milliseconds.\n",
- interval);
out:
*lenp = len;
*ppos += len;
P_ERROR("START DIAG 0xDC for %s failed, "
"return code: %d\n", ops->name, rc);
module_put(ops->owner);
- } else {
- P_INFO("Monitoring %s data enabled, "
- "DIAG 0xDC started.\n", ops->name);
+ } else
ops->active = 1;
- }
} else if ((buf[0] == '0') && (ops->active == 1)) {
ops->active = 0;
rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
(unsigned long) ops->data, ops->size,
ops->mod_lvl);
- if (rc != 0) {
+ if (rc != 0)
P_ERROR("STOP DIAG 0xDC for %s failed, "
"return code: %d\n", ops->name, rc);
- } else {
- P_INFO("Monitoring %s data disabled, "
- "DIAG 0xDC stopped.\n", ops->name);
- }
module_put(ops->owner);
}
spin_unlock(&appldata_ops_lock);
ops->sysctl_header = register_sysctl_table(ops->ctl_table);
if (!ops->sysctl_header)
goto out;
- P_INFO("%s-ops registered!\n", ops->name);
return 0;
out:
spin_lock(&appldata_ops_lock);
spin_unlock(&appldata_ops_lock);
unregister_sysctl_table(ops->sysctl_header);
kfree(ops->ctl_table);
- P_INFO("%s-ops unregistered!\n", ops->name);
}
/********************** module-ops management <END> **************************/
{
int i;
- P_DEBUG("sizeof(parameter_list) = %lu\n",
- sizeof(struct appldata_parameter_list));
-
appldata_wq = create_singlethread_workqueue("appldata");
- if (!appldata_wq) {
- P_ERROR("Could not create work queue\n");
+ if (!appldata_wq)
return -ENOMEM;
- }
get_online_cpus();
for_each_online_cpu(i)
register_hotcpu_notifier(&appldata_nb);
appldata_sysctl_header = register_sysctl_table(appldata_dir_table);
-
- P_DEBUG("Base interface initialized.\n");
return 0;
}
EXPORT_SYMBOL_GPL(appldata_unregister_ops);
EXPORT_SYMBOL_GPL(appldata_diag);
+#ifdef CONFIG_SWAP
EXPORT_SYMBOL_GPL(si_swapinfo);
+#endif
EXPORT_SYMBOL_GPL(nr_threads);
EXPORT_SYMBOL_GPL(nr_running);
EXPORT_SYMBOL_GPL(nr_iowait);
* Time of day based timer functions.
*
* S390 version
- * Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ * Copyright IBM Corp. 1999, 2008
* Author(s): Hartmut Penner (hp@de.ibm.com),
* Martin Schwidefsky (schwidefsky@de.ibm.com),
* Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com)
#include <linux/notifier.h>
#include <linux/clocksource.h>
#include <linux/clockchips.h>
+#include <linux/bootmem.h>
#include <asm/uaccess.h>
#include <asm/delay.h>
#include <asm/s390_ext.h>
/* Enable clock comparator timer interrupt. */
__ctl_set_bit(0,11);
- /* Always allow ETR external interrupts, even without an ETR. */
+ /* Always allow the timing alert external interrupt. */
__ctl_set_bit(0, 4);
}
{
}
+static void etr_timing_alert(struct etr_irq_parm *);
+static void stp_timing_alert(struct stp_irq_parm *);
+
+static void timing_alert_interrupt(__u16 code)
+{
+ if (S390_lowcore.ext_params & 0x00c40000)
+ etr_timing_alert((struct etr_irq_parm *)
+ &S390_lowcore.ext_params);
+ if (S390_lowcore.ext_params & 0x00038000)
+ stp_timing_alert((struct stp_irq_parm *)
+ &S390_lowcore.ext_params);
+}
+
static void etr_reset(void);
-static void etr_ext_handler(__u16);
+static void stp_reset(void);
/*
* Get the TOD clock running.
u64 time;
etr_reset();
+ stp_reset();
if (store_clock(&time) == 0)
return time;
/* TOD clock not running. Set the clock to Unix Epoch. */
if (clocksource_register(&clocksource_tod) != 0)
panic("Could not register TOD clock source");
- /* request the etr external interrupt */
- if (register_early_external_interrupt(0x1406, etr_ext_handler,
+ /* request the timing alert external interrupt */
+ if (register_early_external_interrupt(0x1406,
+ timing_alert_interrupt,
&ext_int_etr_cc) != 0)
panic("Couldn't request external interrupt 0x1406");
#endif
}
+/*
+ * The time is "clock". old is what we think the time is.
+ * Adjust the value by a multiple of jiffies and add the delta to ntp.
+ * "delay" is an approximation how long the synchronization took. If
+ * the time correction is positive, then "delay" is subtracted from
+ * the time difference and only the remaining part is passed to ntp.
+ */
+static unsigned long long adjust_time(unsigned long long old,
+ unsigned long long clock,
+ unsigned long long delay)
+{
+ unsigned long long delta, ticks;
+ struct timex adjust;
+
+ if (clock > old) {
+ /* It is later than we thought. */
+ delta = ticks = clock - old;
+ delta = ticks = (delta < delay) ? 0 : delta - delay;
+ delta -= do_div(ticks, CLK_TICKS_PER_JIFFY);
+ adjust.offset = ticks * (1000000 / HZ);
+ } else {
+ /* It is earlier than we thought. */
+ delta = ticks = old - clock;
+ delta -= do_div(ticks, CLK_TICKS_PER_JIFFY);
+ delta = -delta;
+ adjust.offset = -ticks * (1000000 / HZ);
+ }
+ jiffies_timer_cc += delta;
+ if (adjust.offset != 0) {
+ printk(KERN_NOTICE "etr: time adjusted by %li micro-seconds\n",
+ adjust.offset);
+ adjust.modes = ADJ_OFFSET_SINGLESHOT;
+ do_adjtimex(&adjust);
+ }
+ return delta;
+}
+
+static DEFINE_PER_CPU(atomic_t, clock_sync_word);
+static unsigned long clock_sync_flags;
+
+#define CLOCK_SYNC_HAS_ETR 0
+#define CLOCK_SYNC_HAS_STP 1
+#define CLOCK_SYNC_ETR 2
+#define CLOCK_SYNC_STP 3
+
+/*
+ * The synchronous get_clock function. It will write the current clock
+ * value to the clock pointer and return 0 if the clock is in sync with
+ * the external time source. If the clock mode is local it will return
+ * -ENOSYS and -EAGAIN if the clock is not in sync with the external
+ * reference.
+ */
+int get_sync_clock(unsigned long long *clock)
+{
+ atomic_t *sw_ptr;
+ unsigned int sw0, sw1;
+
+ sw_ptr = &get_cpu_var(clock_sync_word);
+ sw0 = atomic_read(sw_ptr);
+ *clock = get_clock();
+ sw1 = atomic_read(sw_ptr);
+ put_cpu_var(clock_sync_sync);
+ if (sw0 == sw1 && (sw0 & 0x80000000U))
+ /* Success: time is in sync. */
+ return 0;
+ if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags) &&
+ !test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
+ return -ENOSYS;
+ if (!test_bit(CLOCK_SYNC_ETR, &clock_sync_flags) &&
+ !test_bit(CLOCK_SYNC_STP, &clock_sync_flags))
+ return -EACCES;
+ return -EAGAIN;
+}
+EXPORT_SYMBOL(get_sync_clock);
+
+/*
+ * Make get_sync_clock return -EAGAIN.
+ */
+static void disable_sync_clock(void *dummy)
+{
+ atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+ /*
+ * Clear the in-sync bit 2^31. All get_sync_clock calls will
+ * fail until the sync bit is turned back on. In addition
+ * increase the "sequence" counter to avoid the race of an
+ * etr event and the complete recovery against get_sync_clock.
+ */
+ atomic_clear_mask(0x80000000, sw_ptr);
+ atomic_inc(sw_ptr);
+}
+
+/*
+ * Make get_sync_clock return 0 again.
+ * Needs to be called from a context disabled for preemption.
+ */
+static void enable_sync_clock(void)
+{
+ atomic_t *sw_ptr = &__get_cpu_var(clock_sync_word);
+ atomic_set_mask(0x80000000, sw_ptr);
+}
+
/*
* External Time Reference (ETR) code.
*/
static int etr_port0_online;
static int etr_port1_online;
+static int etr_steai_available;
static int __init early_parse_etr(char *p)
{
ETR_EVENT_UPDATE,
};
-enum etr_flags {
- ETR_FLAG_ENOSYS,
- ETR_FLAG_EACCES,
- ETR_FLAG_STEAI,
-};
-
/*
* Valid bit combinations of the eacr register are (x = don't care):
* e0 e1 dp p0 p1 ea es sl
*/
static struct etr_eacr etr_eacr;
static u64 etr_tolec; /* time of last eacr update */
-static unsigned long etr_flags;
static struct etr_aib etr_port0;
static int etr_port0_uptodate;
static struct etr_aib etr_port1;
static int etr_port1_uptodate;
static unsigned long etr_events;
static struct timer_list etr_timer;
-static DEFINE_PER_CPU(atomic_t, etr_sync_word);
static void etr_timeout(unsigned long dummy);
static void etr_work_fn(struct work_struct *work);
static DECLARE_WORK(etr_work, etr_work_fn);
-/*
- * The etr get_clock function. It will write the current clock value
- * to the clock pointer and return 0 if the clock is in sync with the
- * external time source. If the clock mode is local it will return
- * -ENOSYS and -EAGAIN if the clock is not in sync with the external
- * reference. This function is what ETR is all about..
- */
-int get_sync_clock(unsigned long long *clock)
-{
- atomic_t *sw_ptr;
- unsigned int sw0, sw1;
-
- sw_ptr = &get_cpu_var(etr_sync_word);
- sw0 = atomic_read(sw_ptr);
- *clock = get_clock();
- sw1 = atomic_read(sw_ptr);
- put_cpu_var(etr_sync_sync);
- if (sw0 == sw1 && (sw0 & 0x80000000U))
- /* Success: time is in sync. */
- return 0;
- if (test_bit(ETR_FLAG_ENOSYS, &etr_flags))
- return -ENOSYS;
- if (test_bit(ETR_FLAG_EACCES, &etr_flags))
- return -EACCES;
- return -EAGAIN;
-}
-EXPORT_SYMBOL(get_sync_clock);
-
-/*
- * Make get_sync_clock return -EAGAIN.
- */
-static void etr_disable_sync_clock(void *dummy)
-{
- atomic_t *sw_ptr = &__get_cpu_var(etr_sync_word);
- /*
- * Clear the in-sync bit 2^31. All get_sync_clock calls will
- * fail until the sync bit is turned back on. In addition
- * increase the "sequence" counter to avoid the race of an
- * etr event and the complete recovery against get_sync_clock.
- */
- atomic_clear_mask(0x80000000, sw_ptr);
- atomic_inc(sw_ptr);
-}
-
-/*
- * Make get_sync_clock return 0 again.
- * Needs to be called from a context disabled for preemption.
- */
-static void etr_enable_sync_clock(void)
-{
- atomic_t *sw_ptr = &__get_cpu_var(etr_sync_word);
- atomic_set_mask(0x80000000, sw_ptr);
-}
-
/*
* Reset ETR attachment.
*/
.e0 = 0, .e1 = 0, ._pad0 = 4, .dp = 0,
.p0 = 0, .p1 = 0, ._pad1 = 0, .ea = 0,
.es = 0, .sl = 0 };
- if (etr_setr(&etr_eacr) == 0)
+ if (etr_setr(&etr_eacr) == 0) {
etr_tolec = get_clock();
- else {
- set_bit(ETR_FLAG_ENOSYS, &etr_flags);
- if (etr_port0_online || etr_port1_online) {
- printk(KERN_WARNING "Running on non ETR capable "
- "machine, only local mode available.\n");
- etr_port0_online = etr_port1_online = 0;
- }
+ set_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags);
+ } else if (etr_port0_online || etr_port1_online) {
+ printk(KERN_WARNING "Running on non ETR capable "
+ "machine, only local mode available.\n");
+ etr_port0_online = etr_port1_online = 0;
}
}
{
struct etr_aib aib;
- if (test_bit(ETR_FLAG_ENOSYS, &etr_flags))
+ if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags))
return 0;
/* Check if this machine has the steai instruction. */
if (etr_steai(&aib, ETR_STEAI_STEPPING_PORT) == 0)
- set_bit(ETR_FLAG_STEAI, &etr_flags);
+ etr_steai_available = 1;
setup_timer(&etr_timer, etr_timeout, 0UL);
- if (!etr_port0_online && !etr_port1_online)
- set_bit(ETR_FLAG_EACCES, &etr_flags);
if (etr_port0_online) {
set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
schedule_work(&etr_work);
{
if (!etr_eacr.sl)
return;
- etr_disable_sync_clock(NULL);
+ if (test_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
+ disable_sync_clock(NULL);
set_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events);
schedule_work(&etr_work);
}
{
if (!etr_eacr.es)
return;
- etr_disable_sync_clock(NULL);
+ if (test_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
+ disable_sync_clock(NULL);
set_bit(ETR_EVENT_SYNC_CHECK, &etr_events);
schedule_work(&etr_work);
}
/*
- * ETR external interrupt. There are two causes:
+ * ETR timing alert. There are two causes:
* 1) port state change, check the usability of the port
* 2) port alert, one of the ETR-data-validity bits (v1-v2 bits of the
* sldr-status word) or ETR-data word 1 (edf1) or ETR-data word 3 (edf3)
* or ETR-data word 4 (edf4) has changed.
*/
-static void etr_ext_handler(__u16 code)
+static void etr_timing_alert(struct etr_irq_parm *intparm)
{
- struct etr_interruption_parameter *intparm =
- (struct etr_interruption_parameter *) &S390_lowcore.ext_params;
-
if (intparm->pc0)
/* ETR port 0 state change. */
set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
return 1;
}
-/*
- * The time is "clock". old is what we think the time is.
- * Adjust the value by a multiple of jiffies and add the delta to ntp.
- * "delay" is an approximation how long the synchronization took. If
- * the time correction is positive, then "delay" is subtracted from
- * the time difference and only the remaining part is passed to ntp.
- */
-static unsigned long long etr_adjust_time(unsigned long long old,
- unsigned long long clock,
- unsigned long long delay)
-{
- unsigned long long delta, ticks;
- struct timex adjust;
-
- if (clock > old) {
- /* It is later than we thought. */
- delta = ticks = clock - old;
- delta = ticks = (delta < delay) ? 0 : delta - delay;
- delta -= do_div(ticks, CLK_TICKS_PER_JIFFY);
- adjust.offset = ticks * (1000000 / HZ);
- } else {
- /* It is earlier than we thought. */
- delta = ticks = old - clock;
- delta -= do_div(ticks, CLK_TICKS_PER_JIFFY);
- delta = -delta;
- adjust.offset = -ticks * (1000000 / HZ);
- }
- jiffies_timer_cc += delta;
- if (adjust.offset != 0) {
- printk(KERN_NOTICE "etr: time adjusted by %li micro-seconds\n",
- adjust.offset);
- adjust.modes = ADJ_OFFSET_SINGLESHOT;
- do_adjtimex(&adjust);
- }
- return delta;
-}
-
-static struct {
+struct clock_sync_data {
int in_sync;
unsigned long long fixup_cc;
-} etr_sync;
+};
-static void etr_sync_cpu_start(void *dummy)
+static void clock_sync_cpu_start(void *dummy)
{
- etr_enable_sync_clock();
+ struct clock_sync_data *sync = dummy;
+
+ enable_sync_clock();
/*
* This looks like a busy wait loop but it isn't. etr_sync_cpus
* is called on all other cpus while the TOD clocks is stopped.
* __udelay will stop the cpu on an enabled wait psw until the
* TOD is running again.
*/
- while (etr_sync.in_sync == 0) {
+ while (sync->in_sync == 0) {
__udelay(1);
/*
* A different cpu changes *in_sync. Therefore use
*/
barrier();
}
- if (etr_sync.in_sync != 1)
+ if (sync->in_sync != 1)
/* Didn't work. Clear per-cpu in sync bit again. */
- etr_disable_sync_clock(NULL);
+ disable_sync_clock(NULL);
/*
* This round of TOD syncing is done. Set the clock comparator
* to the next tick and let the processor continue.
*/
- fixup_clock_comparator(etr_sync.fixup_cc);
+ fixup_clock_comparator(sync->fixup_cc);
}
-static void etr_sync_cpu_end(void *dummy)
+static void clock_sync_cpu_end(void *dummy)
{
}
static int etr_sync_clock(struct etr_aib *aib, int port)
{
struct etr_aib *sync_port;
+ struct clock_sync_data etr_sync;
unsigned long long clock, old_clock, delay, delta;
int follows;
int rc;
*/
memset(&etr_sync, 0, sizeof(etr_sync));
preempt_disable();
- smp_call_function(clock_sync_cpu_start, &etr_sync, 0, 0);
- smp_call_function(etr_sync_cpu_start, NULL, 0);
++ smp_call_function(clock_sync_cpu_start, &etr_sync, 0);
local_irq_disable();
- etr_enable_sync_clock();
+ enable_sync_clock();
/* Set clock to next OTE. */
__ctl_set_bit(14, 21);
/* Adjust Linux timing variables. */
delay = (unsigned long long)
(aib->edf2.etv - sync_port->edf2.etv) << 32;
- delta = etr_adjust_time(old_clock, clock, delay);
+ delta = adjust_time(old_clock, clock, delay);
etr_sync.fixup_cc = delta;
fixup_clock_comparator(delta);
/* Verify that the clock is properly set. */
if (!etr_aib_follows(sync_port, aib, port)) {
/* Didn't work. */
- etr_disable_sync_clock(NULL);
+ disable_sync_clock(NULL);
etr_sync.in_sync = -EAGAIN;
rc = -EAGAIN;
} else {
/* Could not set the clock ?!? */
__ctl_clear_bit(0, 29);
__ctl_clear_bit(14, 21);
- etr_disable_sync_clock(NULL);
+ disable_sync_clock(NULL);
etr_sync.in_sync = -EAGAIN;
rc = -EAGAIN;
}
local_irq_enable();
- smp_call_function(clock_sync_cpu_end, NULL, 0, 0);
- smp_call_function(etr_sync_cpu_end,NULL,0);
++ smp_call_function(clock_sync_cpu_end, NULL, 0);
preempt_enable();
return rc;
}
* Do not try to get the alternate port aib if the clock
* is not in sync yet.
*/
- if (!eacr.es)
+ if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags) && !eacr.es)
return eacr;
/*
* the other port immediately. If only stetr is available the
* data-port bit toggle has to be used.
*/
- if (test_bit(ETR_FLAG_STEAI, &etr_flags)) {
+ if (etr_steai_available) {
if (eacr.p0 && !etr_port0_uptodate) {
etr_steai_cv(&etr_port0, ETR_STEAI_PORT_0);
etr_port0_uptodate = 1;
if (!eacr.ea) {
/* Both ports offline. Reset everything. */
eacr.dp = eacr.es = eacr.sl = 0;
- on_each_cpu(disable_sync_clock, NULL, 0, 1);
- on_each_cpu(etr_disable_sync_clock, NULL, 1);
++ on_each_cpu(disable_sync_clock, NULL, 1);
del_timer_sync(&etr_timer);
etr_update_eacr(eacr);
- set_bit(ETR_FLAG_EACCES, &etr_flags);
+ clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
return;
}
eacr.e1 = 1;
sync_port = (etr_port0_uptodate &&
etr_port_valid(&etr_port0, 0)) ? 0 : -1;
- clear_bit(ETR_FLAG_EACCES, &etr_flags);
} else if (eacr.p1 && aib.esw.psc1 == etr_lpsc_pps_mode) {
eacr.sl = 0;
eacr.e0 = 0;
eacr.es = 0;
sync_port = (etr_port1_uptodate &&
etr_port_valid(&etr_port1, 1)) ? 1 : -1;
- clear_bit(ETR_FLAG_EACCES, &etr_flags);
} else if (eacr.p0 && aib.esw.psc0 == etr_lpsc_operational_step) {
eacr.sl = 1;
eacr.e0 = 1;
eacr.e1 = 1;
sync_port = (etr_port0_uptodate &&
etr_port_valid(&etr_port0, 0)) ? 0 : -1;
- clear_bit(ETR_FLAG_EACCES, &etr_flags);
} else if (eacr.p1 && aib.esw.psc1 == etr_lpsc_operational_step) {
eacr.sl = 1;
eacr.e0 = 0;
eacr.es = 0;
sync_port = (etr_port1_uptodate &&
etr_port_valid(&etr_port1, 1)) ? 1 : -1;
- clear_bit(ETR_FLAG_EACCES, &etr_flags);
} else {
/* Both ports not usable. */
eacr.es = eacr.sl = 0;
sync_port = -1;
- set_bit(ETR_FLAG_EACCES, &etr_flags);
+ clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
}
+ if (!test_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
+ eacr.es = 0;
+
/*
* If the clock is in sync just update the eacr and return.
* If there is no valid sync port wait for a port update.
*/
- if (eacr.es || sync_port < 0) {
+ if (test_bit(CLOCK_SYNC_STP, &clock_sync_flags) ||
+ eacr.es || sync_port < 0) {
etr_update_eacr(eacr);
etr_set_tolec_timeout(now);
return;
* and set up a timer to try again after 0.5 seconds
*/
etr_update_eacr(eacr);
+ set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
if (now < etr_tolec + (1600000 << 12) ||
etr_sync_clock(&aib, sync_port) != 0) {
/* Sync failed. Try again in 1/2 second. */
eacr.es = 0;
etr_update_eacr(eacr);
+ clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
etr_set_sync_timeout();
} else
etr_set_tolec_timeout(now);
value = simple_strtoul(buf, NULL, 0);
if (value != 0 && value != 1)
return -EINVAL;
- if (test_bit(ETR_FLAG_ENOSYS, &etr_flags))
- return -ENOSYS;
+ if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags))
+ return -EOPNOTSUPP;
if (dev == &etr_port0_dev) {
if (etr_port0_online == value)
return count; /* Nothing to do. */
}
device_initcall(etr_init_sysfs);
+
+/*
+ * Server Time Protocol (STP) code.
+ */
+static int stp_online;
+static struct stp_sstpi stp_info;
+static void *stp_page;
+
+static void stp_work_fn(struct work_struct *work);
+static DECLARE_WORK(stp_work, stp_work_fn);
+
+static int __init early_parse_stp(char *p)
+{
+ if (strncmp(p, "off", 3) == 0)
+ stp_online = 0;
+ else if (strncmp(p, "on", 2) == 0)
+ stp_online = 1;
+ return 0;
+}
+early_param("stp", early_parse_stp);
+
+/*
+ * Reset STP attachment.
+ */
+static void stp_reset(void)
+{
+ int rc;
+
+ stp_page = alloc_bootmem_pages(PAGE_SIZE);
+ rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000);
+ if (rc == 1)
+ set_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags);
+ else if (stp_online) {
+ printk(KERN_WARNING "Running on non STP capable machine.\n");
+ free_bootmem((unsigned long) stp_page, PAGE_SIZE);
+ stp_page = NULL;
+ stp_online = 0;
+ }
+}
+
+static int __init stp_init(void)
+{
+ if (test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags) && stp_online)
+ schedule_work(&stp_work);
+ return 0;
+}
+
+arch_initcall(stp_init);
+
+/*
+ * STP timing alert. There are three causes:
+ * 1) timing status change
+ * 2) link availability change
+ * 3) time control parameter change
+ * In all three cases we are only interested in the clock source state.
+ * If a STP clock source is now available use it.
+ */
+static void stp_timing_alert(struct stp_irq_parm *intparm)
+{
+ if (intparm->tsc || intparm->lac || intparm->tcpc)
+ schedule_work(&stp_work);
+}
+
+/*
+ * STP sync check machine check. This is called when the timing state
+ * changes from the synchronized state to the unsynchronized state.
+ * After a STP sync check the clock is not in sync. The machine check
+ * is broadcasted to all cpus at the same time.
+ */
+void stp_sync_check(void)
+{
+ if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags))
+ return;
+ disable_sync_clock(NULL);
+ schedule_work(&stp_work);
+}
+
+/*
+ * STP island condition machine check. This is called when an attached
+ * server attempts to communicate over an STP link and the servers
+ * have matching CTN ids and have a valid stratum-1 configuration
+ * but the configurations do not match.
+ */
+void stp_island_check(void)
+{
+ if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags))
+ return;
+ disable_sync_clock(NULL);
+ schedule_work(&stp_work);
+}
+
+/*
+ * STP tasklet. Check for the STP state and take over the clock
+ * synchronization if the STP clock source is usable.
+ */
+static void stp_work_fn(struct work_struct *work)
+{
+ struct clock_sync_data stp_sync;
+ unsigned long long old_clock, delta;
+ int rc;
+
+ if (!stp_online) {
+ chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000);
+ return;
+ }
+
+ rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0);
+ if (rc)
+ return;
+
+ rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+ if (rc || stp_info.c == 0)
+ return;
+
+ /*
+ * Catch all other cpus and make them wait until we have
+ * successfully synced the clock. smp_call_function will
+ * return after all other cpus are in clock_sync_cpu_start.
+ */
+ memset(&stp_sync, 0, sizeof(stp_sync));
+ preempt_disable();
+ smp_call_function(clock_sync_cpu_start, &stp_sync, 0, 0);
+ local_irq_disable();
+ enable_sync_clock();
+
+ set_bit(CLOCK_SYNC_STP, &clock_sync_flags);
+ if (test_and_clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
+ schedule_work(&etr_work);
+
+ rc = 0;
+ if (stp_info.todoff[0] || stp_info.todoff[1] ||
+ stp_info.todoff[2] || stp_info.todoff[3] ||
+ stp_info.tmd != 2) {
+ old_clock = get_clock();
+ rc = chsc_sstpc(stp_page, STP_OP_SYNC, 0);
+ if (rc == 0) {
+ delta = adjust_time(old_clock, get_clock(), 0);
+ fixup_clock_comparator(delta);
+ rc = chsc_sstpi(stp_page, &stp_info,
+ sizeof(struct stp_sstpi));
+ if (rc == 0 && stp_info.tmd != 2)
+ rc = -EAGAIN;
+ }
+ }
+ if (rc) {
+ disable_sync_clock(NULL);
+ stp_sync.in_sync = -EAGAIN;
+ clear_bit(CLOCK_SYNC_STP, &clock_sync_flags);
+ if (etr_port0_online || etr_port1_online)
+ schedule_work(&etr_work);
+ } else
+ stp_sync.in_sync = 1;
+
+ local_irq_enable();
+ smp_call_function(clock_sync_cpu_end, NULL, 0, 0);
+ preempt_enable();
+}
+
+/*
+ * STP class sysfs interface functions
+ */
+static struct sysdev_class stp_sysclass = {
+ .name = "stp",
+};
+
+static ssize_t stp_ctn_id_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online)
+ return -ENODATA;
+ return sprintf(buf, "%016llx\n",
+ *(unsigned long long *) stp_info.ctnid);
+}
+
+static SYSDEV_CLASS_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL);
+
+static ssize_t stp_ctn_type_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online)
+ return -ENODATA;
+ return sprintf(buf, "%i\n", stp_info.ctn);
+}
+
+static SYSDEV_CLASS_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL);
+
+static ssize_t stp_dst_offset_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online || !(stp_info.vbits & 0x2000))
+ return -ENODATA;
+ return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+}
+
+static SYSDEV_CLASS_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL);
+
+static ssize_t stp_leap_seconds_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online || !(stp_info.vbits & 0x8000))
+ return -ENODATA;
+ return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+}
+
+static SYSDEV_CLASS_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL);
+
+static ssize_t stp_stratum_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online)
+ return -ENODATA;
+ return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+}
+
+static SYSDEV_CLASS_ATTR(stratum, 0400, stp_stratum_show, NULL);
+
+static ssize_t stp_time_offset_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online || !(stp_info.vbits & 0x0800))
+ return -ENODATA;
+ return sprintf(buf, "%i\n", (int) stp_info.tto);
+}
+
+static SYSDEV_CLASS_ATTR(time_offset, 0400, stp_time_offset_show, NULL);
+
+static ssize_t stp_time_zone_offset_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online || !(stp_info.vbits & 0x4000))
+ return -ENODATA;
+ return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+}
+
+static SYSDEV_CLASS_ATTR(time_zone_offset, 0400,
+ stp_time_zone_offset_show, NULL);
+
+static ssize_t stp_timing_mode_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online)
+ return -ENODATA;
+ return sprintf(buf, "%i\n", stp_info.tmd);
+}
+
+static SYSDEV_CLASS_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL);
+
+static ssize_t stp_timing_state_show(struct sysdev_class *class, char *buf)
+{
+ if (!stp_online)
+ return -ENODATA;
+ return sprintf(buf, "%i\n", stp_info.tst);
+}
+
+static SYSDEV_CLASS_ATTR(timing_state, 0400, stp_timing_state_show, NULL);
+
+static ssize_t stp_online_show(struct sysdev_class *class, char *buf)
+{
+ return sprintf(buf, "%i\n", stp_online);
+}
+
+static ssize_t stp_online_store(struct sysdev_class *class,
+ const char *buf, size_t count)
+{
+ unsigned int value;
+
+ value = simple_strtoul(buf, NULL, 0);
+ if (value != 0 && value != 1)
+ return -EINVAL;
+ if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
+ return -EOPNOTSUPP;
+ stp_online = value;
+ schedule_work(&stp_work);
+ return count;
+}
+
+/*
+ * Can't use SYSDEV_CLASS_ATTR because the attribute should be named
+ * stp/online but attr_online already exists in this file ..
+ */
+static struct sysdev_class_attribute attr_stp_online = {
+ .attr = { .name = "online", .mode = 0600 },
+ .show = stp_online_show,
+ .store = stp_online_store,
+};
+
+static struct sysdev_class_attribute *stp_attributes[] = {
+ &attr_ctn_id,
+ &attr_ctn_type,
+ &attr_dst_offset,
+ &attr_leap_seconds,
+ &attr_stp_online,
+ &attr_stratum,
+ &attr_time_offset,
+ &attr_time_zone_offset,
+ &attr_timing_mode,
+ &attr_timing_state,
+ NULL
+};
+
+static int __init stp_init_sysfs(void)
+{
+ struct sysdev_class_attribute **attr;
+ int rc;
+
+ rc = sysdev_class_register(&stp_sysclass);
+ if (rc)
+ goto out;
+ for (attr = stp_attributes; *attr; attr++) {
+ rc = sysdev_class_create_file(&stp_sysclass, *attr);
+ if (rc)
+ goto out_unreg;
+ }
+ return 0;
+out_unreg:
+ for (; attr >= stp_attributes; attr--)
+ sysdev_class_remove_file(&stp_sysclass, *attr);
+ sysdev_class_unregister(&stp_sysclass);
+out:
+ return rc;
+}
+
+device_initcall(stp_init_sysfs);
select HAVE_OPROFILE
select HAVE_KPROBES
select HAVE_KRETPROBES
+ select HAVE_DYNAMIC_FTRACE
+ select HAVE_FTRACE
select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
select HAVE_ARCH_KGDB if !X86_VOYAGER
def_bool y
config HAVE_SETUP_PER_CPU_AREA
- def_bool X86_64 || (X86_SMP && !X86_VOYAGER)
+ def_bool X86_64_SMP || (X86_SMP && !X86_VOYAGER)
config HAVE_CPUMASK_OF_CPU_MAP
def_bool X86_64_SMP
config X86_SMP
bool
depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64)
+ select USE_GENERIC_SMP_HELPERS
default y
config X86_32_SMP
config X86_HT
bool
depends on SMP
- depends on (X86_32 && !(X86_VISWS || X86_VOYAGER)) || X86_64
+ depends on (X86_32 && !X86_VOYAGER) || X86_64
default y
config X86_BIOS_REBOOT
bool
- depends on !X86_VISWS && !X86_VOYAGER
+ depends on !X86_VOYAGER
default y
config X86_TRAMPOLINE
If you don't know what to do here, say N.
+config X86_FIND_SMP_CONFIG
+ def_bool y
+ depends on X86_MPPARSE || X86_VOYAGER
+
+if ACPI
+config X86_MPPARSE
+ def_bool y
+ bool "Enable MPS table"
+ depends on X86_LOCAL_APIC
+ help
+ For old smp systems that do not have proper acpi support. Newer systems
+ (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
+endif
+
+if !ACPI
+config X86_MPPARSE
+ def_bool y
+ depends on X86_LOCAL_APIC
+endif
+
choice
prompt "Subarchitecture Type"
default X86_PC
config X86_VOYAGER
bool "Voyager (NCR)"
- depends on X86_32 && (SMP || BROKEN)
+ depends on X86_32 && (SMP || BROKEN) && !PCI
help
Voyager is an MCA-based 32-way capable SMP architecture proprietary
to NCR Corp. Machine classes 345x/35xx/4100/51xx are Voyager-based.
If you do not specifically know you have a Voyager based machine,
say N here, otherwise the kernel you build will not be bootable.
+config X86_GENERICARCH
+ bool "Generic architecture"
+ depends on X86_32
+ help
+ This option compiles in the NUMAQ, Summit, bigsmp, ES7000, default
+ subarchitectures. It is intended for a generic binary kernel.
+ if you select them all, kernel will probe it one by one. and will
+ fallback to default.
+
+if X86_GENERICARCH
+
config X86_NUMAQ
bool "NUMAQ (IBM/Sequent)"
- depends on SMP && X86_32
+ depends on SMP && X86_32 && PCI && X86_MPPARSE
select NUMA
help
- This option is used for getting Linux to run on a (IBM/Sequent) NUMA
- multiquad box. This changes the way that processors are bootstrapped,
- and uses Clustered Logical APIC addressing mode instead of Flat Logical.
- You will need a new lynxer.elf file to flash your firmware with - send
- email to <Martin.Bligh@us.ibm.com>.
+ This option is used for getting Linux to run on a NUMAQ (IBM/Sequent)
+ NUMA multiquad box. This changes the way that processors are
+ bootstrapped, and uses Clustered Logical APIC addressing mode instead
+ of Flat Logical. You will need a new lynxer.elf file to flash your
+ firmware with - send email to <Martin.Bligh@us.ibm.com>.
config X86_SUMMIT
bool "Summit/EXA (IBM x440)"
This option is needed for IBM systems that use the Summit/EXA chipset.
In particular, it is needed for the x440.
- If you don't have one of these computers, you should say N here.
- If you want to build a NUMA kernel, you must select ACPI.
+config X86_ES7000
+ bool "Support for Unisys ES7000 IA32 series"
+ depends on X86_32 && SMP
+ help
+ Support for Unisys ES7000 systems. Say 'Y' here if this kernel is
+ supposed to run on an IA32-based Unisys ES7000 system.
config X86_BIGSMP
- bool "Support for other sub-arch SMP systems with more than 8 CPUs"
+ bool "Support for big SMP systems with more than 8 CPUs"
depends on X86_32 && SMP
help
This option is needed for the systems that have more than 8 CPUs
and if the system is not of any sub-arch type above.
- If you don't have such a system, you should say N here.
-
-config X86_VISWS
- bool "SGI 320/540 (Visual Workstation)"
- depends on X86_32
- help
- The SGI Visual Workstation series is an IA32-based workstation
- based on SGI systems chips with some legacy PC hardware attached.
-
- Say Y here to create a kernel to run on the SGI 320 or 540.
-
- A kernel compiled for the Visual Workstation will not run on PCs
- and vice versa. See <file:Documentation/sgi-visws.txt> for details.
-
-config X86_GENERICARCH
- bool "Generic architecture (Summit, bigsmp, ES7000, default)"
- depends on X86_32
- help
- This option compiles in the Summit, bigsmp, ES7000, default subarchitectures.
- It is intended for a generic binary kernel.
- If you want a NUMA kernel, select ACPI. We need SRAT for NUMA.
-
-config X86_ES7000
- bool "Support for Unisys ES7000 IA32 series"
- depends on X86_32 && SMP
- help
- Support for Unisys ES7000 systems. Say 'Y' here if this kernel is
- supposed to run on an IA32-based Unisys ES7000 system.
- Only choose this option if you have such a system, otherwise you
- should say N here.
+endif
config X86_RDC321X
bool "RDC R-321x SoC"
config X86_VSMP
bool "Support for ScaleMP vSMP"
select PARAVIRT
- depends on X86_64
+ depends on X86_64 && PCI
help
Support for ScaleMP vSMP systems. Say 'Y' here if this kernel is
supposed to run on these EM64T-based machines. Only choose this option
endchoice
+config X86_VISWS
+ bool "SGI 320/540 (Visual Workstation)"
+ depends on X86_32 && PCI && !X86_VOYAGER && X86_MPPARSE && PCI_GODIRECT
+ help
+ The SGI Visual Workstation series is an IA32-based workstation
+ based on SGI systems chips with some legacy PC hardware attached.
+
+ Say Y here to create a kernel to run on the SGI 320 or 540.
+
+ A kernel compiled for the Visual Workstation will run on general
+ PCs as well. See <file:Documentation/sgi-visws.txt> for details.
+
config SCHED_NO_NO_OMIT_FRAME_POINTER
def_bool y
prompt "Single-depth WCHAN output"
bool "VMI Guest support"
select PARAVIRT
depends on X86_32
- depends on !(X86_VISWS || X86_VOYAGER)
+ depends on !X86_VOYAGER
help
VMI provides a paravirtualized interface to the VMware ESX server
(it could be used by other hypervisors in theory too, but is not
bool "KVM paravirtualized clock"
select PARAVIRT
select PARAVIRT_CLOCK
- depends on !(X86_VISWS || X86_VOYAGER)
+ depends on !X86_VOYAGER
help
Turning on this option will allow you to run a paravirtualized clock
when running over the KVM hypervisor. Instead of relying on a PIT
config KVM_GUEST
bool "KVM Guest support"
select PARAVIRT
- depends on !(X86_VISWS || X86_VOYAGER)
+ depends on !X86_VOYAGER
help
This option enables various optimizations for running under the KVM
hypervisor.
config PARAVIRT
bool "Enable paravirtualization code"
- depends on !(X86_VISWS || X86_VOYAGER)
+ depends on !X86_VOYAGER
help
This changes the kernel so it can modify itself when it is run
under a hypervisor, potentially improving performance significantly
endif
-config MEMTEST_BOOTPARAM
- bool "Memtest boot parameter"
+config PARAVIRT_DEBUG
+ bool "paravirt-ops debugging"
+ depends on PARAVIRT && DEBUG_KERNEL
+ help
+ Enable to debug paravirt_ops internals. Specifically, BUG if
+ a paravirt_op is missing when it is called.
+
+config MEMTEST
+ bool "Memtest"
depends on X86_64
- default y
help
This option adds a kernel parameter 'memtest', which allows memtest
- to be disabled at boot. If this option is selected, memtest
- functionality can be disabled with memtest=0 on the kernel
- command line. The purpose of this option is to allow a single
- kernel image to be distributed with memtest built in, but not
- necessarily enabled.
-
- If you are unsure how to answer this question, answer Y.
-
-config MEMTEST_BOOTPARAM_VALUE
- int "Memtest boot parameter default value (0-4)"
- depends on MEMTEST_BOOTPARAM
- range 0 4
- default 0
- help
- This option sets the default value for the kernel parameter
- 'memtest', which allows memtest to be disabled at boot. If this
- option is set to 0 (zero), the memtest kernel parameter will
- default to 0, disabling memtest at bootup. If this option is
- set to 4, the memtest kernel parameter will default to 4,
- enabling memtest at bootup, and use that as pattern number.
-
- If you are unsure how to answer this question, answer 0.
-
-config ACPI_SRAT
- def_bool y
- depends on X86_32 && ACPI && NUMA && (X86_SUMMIT || X86_GENERICARCH)
- select ACPI_NUMA
-
-config HAVE_ARCH_PARSE_SRAT
- def_bool y
- depends on ACPI_SRAT
+ to be set.
+ memtest=0, mean disabled; -- default
+ memtest=1, mean do 1 test pattern;
+ ...
+ memtest=4, mean do 4 test patterns.
+ If you are unsure how to answer this question, answer N.
config X86_SUMMIT_NUMA
def_bool y
- depends on X86_32 && NUMA && (X86_SUMMIT || X86_GENERICARCH)
+ depends on X86_32 && NUMA && X86_GENERICARCH
config X86_CYCLONE_TIMER
def_bool y
- depends on X86_32 && X86_SUMMIT || X86_GENERICARCH
+ depends on X86_GENERICARCH
config ES7000_CLUSTERED_APIC
def_bool y
Calgary anyway, pass 'iommu=calgary' on the kernel command line.
If unsure, say Y.
+config AMD_IOMMU
+ bool "AMD IOMMU support"
+ select SWIOTLB
+ depends on X86_64 && PCI && ACPI
+ help
+ With this option you can enable support for AMD IOMMU hardware in
+ your system. An IOMMU is a hardware component which provides
+ remapping of DMA memory accesses from devices. With an AMD IOMMU you
+ can isolate the the DMA memory of different devices and protect the
+ system from misbehaving device drivers or hardware.
+
+ You can find out if your system has an AMD IOMMU if you look into
+ your BIOS for an option to enable it or if you have an IVRS ACPI
+ table.
+
# need this always selected by IOMMU for the VIA workaround
config SWIOTLB
bool
3 GB of memory. If unsure, say Y.
config IOMMU_HELPER
- def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB)
+ def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU)
+config MAXSMP
+ bool "Configure Maximum number of SMP Processors and NUMA Nodes"
+ depends on X86_64 && SMP
+ default n
+ help
+ Configure maximum number of CPUS and NUMA Nodes for this architecture.
+ If unsure, say N.
+if MAXSMP
config NR_CPUS
- int "Maximum number of CPUs (2-255)"
- range 2 255
+ int
+ default "4096"
+endif
+
+if !MAXSMP
+config NR_CPUS
+ int "Maximum number of CPUs (2-4096)"
+ range 2 4096
depends on SMP
default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000
default "8"
help
This allows you to specify the maximum number of CPUs which this
- kernel will support. The maximum supported value is 255 and the
+ kernel will support. The maximum supported value is 4096 and the
minimum value which makes sense is 2.
This is purely to save memory - each supported CPU adds
approximately eight kilobytes to the kernel image.
+endif
config SCHED_SMT
bool "SMT (Hyperthreading) scheduler support"
config X86_UP_APIC
bool "Local APIC support on uniprocessors"
- depends on X86_32 && !SMP && !(X86_VISWS || X86_VOYAGER || X86_GENERICARCH)
+ depends on X86_32 && !SMP && !(X86_VOYAGER || X86_GENERICARCH)
help
A local APIC (Advanced Programmable Interrupt Controller) is an
integrated interrupt controller in the CPU. If you have a single-CPU
config X86_LOCAL_APIC
def_bool y
- depends on X86_64 || (X86_32 && (X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER) || X86_GENERICARCH))
+ depends on X86_64 || (X86_32 && (X86_UP_APIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH))
config X86_IO_APIC
def_bool y
- depends on X86_64 || (X86_32 && (X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER)) || X86_GENERICARCH))
+ depends on X86_64 || (X86_32 && (X86_UP_IOAPIC || (SMP && !X86_VOYAGER) || X86_GENERICARCH))
config X86_VISWS_APIC
def_bool y
config X86_MCE_P4THERMAL
bool "check for P4 thermal throttling interrupt."
- depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP) && !X86_VISWS
+ depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP)
help
Enabling this feature will cause a message to be printed when the P4
enters thermal throttling.
config NUMA
bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
depends on SMP
- depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) && EXPERIMENTAL)
+ depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
default n if X86_PC
- default y if (X86_NUMAQ || X86_SUMMIT)
+ default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
help
Enable NUMA (Non Uniform Memory Access) support.
The kernel will try to allocate memory used by a CPU on the
into virtual nodes when booted with "numa=fake=N", where N is the
number of nodes. This is only useful for debugging.
+if MAXSMP
+
config NODES_SHIFT
- int "Max num nodes shift(1-15)"
- range 1 15 if X86_64
+ int
+ default "9"
+endif
+
+if !MAXSMP
+config NODES_SHIFT
+ int "Maximum NUMA Nodes (as a power of 2)"
+ range 1 9 if X86_64
default "6" if X86_64
default "4" if X86_NUMAQ
default "3"
depends on NEED_MULTIPLE_NODES
+ help
+ Specify the maximum number of NUMA Nodes available on the target
+ system. Increases memory reserved to accomodate various tables.
+endif
config HAVE_ARCH_BOOTMEM_NODE
def_bool y
See <file:Documentation/mtrr.txt> for more information.
+config MTRR_SANITIZER
+ bool
+ prompt "MTRR cleanup support"
+ depends on MTRR
+ help
+ Convert MTRR layout from continuous to discrete, so X drivers can
+ add writeback entries.
+
+ Can be disabled with disable_mtrr_cleanup on the kernel command line.
+ The largest mtrr entry size for a continous block can be set with
+ mtrr_chunk_size.
+
+ If unsure, say N.
+
+config MTRR_SANITIZER_ENABLE_DEFAULT
+ int "MTRR cleanup enable value (0-1)"
+ range 0 1
+ default "0"
+ depends on MTRR_SANITIZER
+ help
+ Enable mtrr cleanup default value
+
+config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT
+ int "MTRR cleanup spare reg num (0-7)"
+ range 0 7
+ default "1"
+ depends on MTRR_SANITIZER
+ help
+ mtrr cleanup spare entries default, it can be changed via
+ mtrr_spare_reg_nr=N on the kernel command line.
+
config X86_PAT
bool
prompt "x86 PAT support"
config CRASH_DUMP
bool "kernel crash dumps (EXPERIMENTAL)"
- depends on EXPERIMENTAL
depends on X86_64 || (X86_32 && HIGHMEM)
help
Generate crash dump after being started by kexec.
menuconfig APM
tristate "APM (Advanced Power Management) BIOS support"
- depends on X86_32 && PM_SLEEP && !X86_VISWS
+ depends on X86_32 && PM_SLEEP
---help---
APM is a BIOS specification for saving power using several different
techniques. This is mostly useful for battery powered laptops with
menu "Bus options (PCI etc.)"
config PCI
- bool "PCI support" if !X86_VISWS && !X86_VSMP
- depends on !X86_VOYAGER
+ bool "PCI support"
default y
select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC)
help
choice
prompt "PCI access mode"
- depends on X86_32 && PCI && !X86_VISWS
+ depends on X86_32 && PCI
default PCI_GOANY
---help---
On PCI systems, the BIOS can be used to detect the PCI devices and
config PCI_BIOS
def_bool y
- depends on X86_32 && !X86_VISWS && PCI && (PCI_GOBIOS || PCI_GOANY)
+ depends on X86_32 && PCI && (PCI_GOBIOS || PCI_GOANY)
# x86-64 doesn't support PCI BIOS access from long mode so always go direct.
config PCI_DIRECT
def_bool y
- depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC) || X86_VISWS)
+ depends on PCI && (X86_64 || (PCI_GODIRECT || PCI_GOANY || PCI_GOOLPC))
config PCI_MMCONFIG
def_bool y
config ISA
bool "ISA support"
- depends on !(X86_VOYAGER || X86_VISWS)
+ depends on !X86_VOYAGER
help
Find out whether you have ISA slots on your motherboard. ISA is the
name of a bus system, i.e. the way the CPU talks to the other stuff
source "drivers/eisa/Kconfig"
config MCA
- bool "MCA support" if !(X86_VISWS || X86_VOYAGER)
+ bool "MCA support" if !X86_VOYAGER
default y if X86_VOYAGER
help
MicroChannel Architecture is found in some IBM PS/2 machines and
unsigned long mp_lapic_addr;
-DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID;
-EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
/*
* Knob to control our willingness to enable the local APIC.
*
- * -1=force-disable, +1=force-enable
+ * +1=force-enable
*/
-static int enable_local_apic __initdata;
+static int force_enable_local_apic;
+int disable_apic;
/* Local APIC timer verification ok */
static int local_apic_timer_verify_ok;
-/* Disable local APIC timer from the kernel commandline or via dmi quirk
- or using CPU MSR check */
-int local_apic_timer_disabled;
+/* Disable local APIC timer from the kernel commandline or via dmi quirk */
+static int local_apic_timer_disabled;
/* Local APIC timer works in C2 */
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
+int first_system_vector = 0xfe;
+
+char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+
/*
* Debug level, exported for io_apic.c
*/
int apic_verbosity;
+int pic_mode;
+
+/* Have we found an MP table */
+int smp_found_config;
+
+static struct resource lapic_resource = {
+ .name = "Local APIC",
+ .flags = IORESOURCE_MEM | IORESOURCE_BUSY,
+};
+
static unsigned int calibration_result;
static int lapic_next_event(unsigned long delta,
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
else
printk(KERN_WARNING "APIC timer registered as dummy,"
- " due to nmi_watchdog=1!\n");
+ " due to nmi_watchdog=%d!\n", nmi_watchdog);
}
/* Setup the lapic or request the broadcast */
* Double-check whether this APIC is really registered.
*/
if (!apic_id_registered())
- BUG();
+ WARN_ON_ONCE(1);
/*
* Intel recommends to set DFR, LDR and TPR before enabling
u32 h, l, features;
/* Disabled by kernel option? */
- if (enable_local_apic < 0)
+ if (disable_apic)
return -1;
switch (boot_cpu_data.x86_vendor) {
* Over-ride BIOS and try to enable the local APIC only if
* "lapic" specified.
*/
- if (enable_local_apic <= 0) {
+ if (!force_enable_local_apic) {
printk(KERN_INFO "Local APIC disabled by BIOS -- "
"you can enable it with \"lapic\"\n");
return -1;
if (l & MSR_IA32_APICBASE_ENABLE)
mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
- if (nmi_watchdog != NMI_NONE && nmi_watchdog != NMI_DISABLED)
- nmi_watchdog = NMI_LOCAL_APIC;
-
printk(KERN_INFO "Found and enabled local APIC!\n");
apic_pm_activate();
if (boot_cpu_physical_apicid == -1U)
boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
-#ifdef CONFIG_X86_IO_APIC
- {
- unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
- int i;
-
- for (i = 0; i < nr_ioapics; i++) {
- if (smp_found_config) {
- ioapic_phys = mp_ioapics[i].mpc_apicaddr;
- if (!ioapic_phys) {
- printk(KERN_ERR
- "WARNING: bogus zero IO-APIC "
- "address found in MPTABLE, "
- "disabling IO/APIC support!\n");
- smp_found_config = 0;
- skip_ioapic_setup = 1;
- goto fake_ioapic_page;
- }
- } else {
-fake_ioapic_page:
- ioapic_phys = (unsigned long)
- alloc_bootmem_pages(PAGE_SIZE);
- ioapic_phys = __pa(ioapic_phys);
- }
- set_fixmap_nocache(idx, ioapic_phys);
- printk(KERN_DEBUG "mapped IOAPIC to %08lx (%08lx)\n",
- __fix_to_virt(idx), ioapic_phys);
- idx++;
- }
- }
-#endif
}
/*
int __init APIC_init_uniprocessor(void)
{
- if (enable_local_apic < 0)
+ if (disable_apic)
clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
if (!smp_found_config && !cpu_has_apic)
#ifdef CONFIG_CRASH_DUMP
boot_cpu_physical_apicid = GET_APIC_ID(read_apic_id());
#endif
- phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+ physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
setup_local_APIC();
+#ifdef CONFIG_X86_IO_APIC
+ if (!smp_found_config || skip_ioapic_setup || !nr_ioapics)
+#endif
+ localise_nmi_watchdog();
end_local_APIC_setup();
#ifdef CONFIG_X86_IO_APIC
if (smp_found_config)
* The reschedule interrupt is a CPU-to-CPU reschedule-helper
* IPI, driven by wakeup.
*/
- set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+ alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
/* IPI for invalidation */
- set_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
/* IPI for generic function call */
- set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+ alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+
+ /* IPI for single call function */
+ set_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
+ call_function_single_interrupt);
}
#endif
smp_intr_init();
#endif
/* self generated IPI for local APIC timer */
- set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
/* IPI vectors for APIC spurious and error interrupts */
- set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
- set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+ alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
/* thermal monitor LVT interrupt */
#ifdef CONFIG_X86_MCE_P4THERMAL
- set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+ alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
#endif
}
*/
cpu = 0;
+ if (apicid > max_physical_apicid)
+ max_physical_apicid = apicid;
+
/*
* Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y
* but we need to work other dependencies like SMP_SUSPEND etc
* if (CPU_HOTPLUG_ENABLED || num_processors > 8)
* - Ashok Raj <ashok.raj@intel.com>
*/
- if (num_processors > 8) {
+ if (max_physical_apicid >= 8) {
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_INTEL:
if (!APIC_XAPIC(version)) {
}
#ifdef CONFIG_SMP
/* are we being called early in kernel startup? */
- if (x86_cpu_to_apicid_early_ptr) {
- u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;
- u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+ if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
+ u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+ u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
cpu_to_apicid[cpu] = apicid;
bios_cpu_apicid[cpu] = apicid;
*/
static int __init parse_lapic(char *arg)
{
- enable_local_apic = 1;
+ force_enable_local_apic = 1;
return 0;
}
early_param("lapic", parse_lapic);
static int __init parse_nolapic(char *arg)
{
- enable_local_apic = -1;
+ disable_apic = 1;
clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
return 0;
}
}
__setup("apic=", apic_set_verbosity);
+static int __init lapic_insert_resource(void)
+{
+ if (!apic_phys)
+ return -1;
+
+ /* Put local APIC into the resource map. */
+ lapic_resource.start = apic_phys;
+ lapic_resource.end = lapic_resource.start + PAGE_SIZE - 1;
+ insert_resource(&iomem_resource, &lapic_resource);
+
+ return 0;
+}
+
+/*
+ * need call insert after e820_reserve_resources()
+ * that is using request_resource
+ */
+late_initcall(lapic_insert_resource);
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
+#include <linux/smp_lock.h>
#include <linux/string.h>
#include <linux/rcupdate.h>
#include <linux/kallsyms.h>
#include <asm/idle.h>
#define MISC_MCELOG_MINOR 227
-#define NR_BANKS 6
+#define NR_SYSFS_BANKS 6
atomic_t mce_entry;
*/
static int tolerant = 1;
static int banks;
-static unsigned long bank[NR_BANKS] = { [0 ... NR_BANKS-1] = ~0UL };
+static unsigned long bank[NR_SYSFS_BANKS] = { [0 ... NR_SYSFS_BANKS-1] = ~0UL };
static unsigned long notify_user;
static int rip_msr;
static int mce_bootlog = -1;
barrier();
for (i = 0; i < banks; i++) {
- if (!bank[i])
+ if (i < NR_SYSFS_BANKS && !bank[i])
continue;
m.misc = 0;
static void mcheck_timer(struct work_struct *work)
{
- on_each_cpu(mcheck_check_cpu, NULL, 1, 1);
+ on_each_cpu(mcheck_check_cpu, NULL, 1);
/*
* Alert userspace if needed. If we logged an MCE, reduce the
rdmsrl(MSR_IA32_MCG_CAP, cap);
banks = cap & 0xff;
- if (banks > NR_BANKS) {
- printk(KERN_INFO "MCE: warning: using only %d banks\n", banks);
- banks = NR_BANKS;
+ if (banks > MCE_EXTENDED_BANK) {
+ banks = MCE_EXTENDED_BANK;
+ printk(KERN_INFO "MCE: warning: using only %d banks\n",
+ MCE_EXTENDED_BANK);
}
/* Use accurate RIP reporting if available. */
if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9)
wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
for (i = 0; i < banks; i++) {
- wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
+ if (i < NR_SYSFS_BANKS)
+ wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]);
+ else
+ wrmsrl(MSR_IA32_MC0_CTL+4*i, ~0UL);
+
wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0);
}
}
static int mce_open(struct inode *inode, struct file *file)
{
+ lock_kernel();
spin_lock(&mce_state_lock);
if (open_exclu || (open_count && (file->f_flags & O_EXCL))) {
spin_unlock(&mce_state_lock);
+ unlock_kernel();
return -EBUSY;
}
open_count++;
spin_unlock(&mce_state_lock);
+ unlock_kernel();
return nonseekable_open(inode, file);
}
* Collect entries that were still getting written before the
* synchronize.
*/
- on_each_cpu(collect_tscs, cpu_tsc, 1, 1);
+ on_each_cpu(collect_tscs, cpu_tsc, 1);
for (i = next; i < MCE_LOG_LEN; i++) {
if (mcelog.entry[i].finished &&
mcelog.entry[i].tsc < cpu_tsc[mcelog.entry[i].cpu]) {
if (next_interval)
cancel_delayed_work(&mcheck_work);
/* Timer race is harmless here */
- on_each_cpu(mce_init, NULL, 1, 1);
+ on_each_cpu(mce_init, NULL, 1);
next_interval = check_interval * HZ;
if (next_interval)
schedule_delayed_work(&mcheck_work,
} \
static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name);
-/* TBD should generate these dynamically based on number of available banks */
+/*
+ * TBD should generate these dynamically based on number of available banks.
+ * Have only 6 contol banks in /sysfs until then.
+ */
ACCESSOR(bank0ctl,bank[0],mce_restart())
ACCESSOR(bank1ctl,bank[1],mce_restart())
ACCESSOR(bank2ctl,bank[2],mce_restart())
#include <linux/smp.h>
#include <linux/cpu.h>
#include <linux/mutex.h>
+#include <linux/sort.h>
#include <asm/e820.h>
#include <asm/mtrr.h>
atomic_set(&data.gate,0);
/* Start the ball rolling on other CPUs */
- if (smp_call_function(ipi_handler, &data, 1, 0) != 0)
+ if (smp_call_function(ipi_handler, &data, 0) != 0)
panic("mtrr: timed out waiting for other CPUs\n");
local_irq_save(flags);
.resume = mtrr_restore,
};
+/* should be related to MTRR_VAR_RANGES nums */
+#define RANGE_NUM 256
+
+struct res_range {
+ unsigned long start;
+ unsigned long end;
+};
+
+static int __init
+add_range(struct res_range *range, int nr_range, unsigned long start,
+ unsigned long end)
+{
+ /* out of slots */
+ if (nr_range >= RANGE_NUM)
+ return nr_range;
+
+ range[nr_range].start = start;
+ range[nr_range].end = end;
+
+ nr_range++;
+
+ return nr_range;
+}
+
+static int __init
+add_range_with_merge(struct res_range *range, int nr_range, unsigned long start,
+ unsigned long end)
+{
+ int i;
+
+ /* try to merge it with old one */
+ for (i = 0; i < nr_range; i++) {
+ unsigned long final_start, final_end;
+ unsigned long common_start, common_end;
+
+ if (!range[i].end)
+ continue;
+
+ common_start = max(range[i].start, start);
+ common_end = min(range[i].end, end);
+ if (common_start > common_end + 1)
+ continue;
+
+ final_start = min(range[i].start, start);
+ final_end = max(range[i].end, end);
+
+ range[i].start = final_start;
+ range[i].end = final_end;
+ return nr_range;
+ }
+
+ /* need to add that */
+ return add_range(range, nr_range, start, end);
+}
+
+static void __init
+subtract_range(struct res_range *range, unsigned long start, unsigned long end)
+{
+ int i, j;
+
+ for (j = 0; j < RANGE_NUM; j++) {
+ if (!range[j].end)
+ continue;
+
+ if (start <= range[j].start && end >= range[j].end) {
+ range[j].start = 0;
+ range[j].end = 0;
+ continue;
+ }
+
+ if (start <= range[j].start && end < range[j].end &&
+ range[j].start < end + 1) {
+ range[j].start = end + 1;
+ continue;
+ }
+
+
+ if (start > range[j].start && end >= range[j].end &&
+ range[j].end > start - 1) {
+ range[j].end = start - 1;
+ continue;
+ }
+
+ if (start > range[j].start && end < range[j].end) {
+ /* find the new spare */
+ for (i = 0; i < RANGE_NUM; i++) {
+ if (range[i].end == 0)
+ break;
+ }
+ if (i < RANGE_NUM) {
+ range[i].end = range[j].end;
+ range[i].start = end + 1;
+ } else {
+ printk(KERN_ERR "run of slot in ranges\n");
+ }
+ range[j].end = start - 1;
+ continue;
+ }
+ }
+}
+
+static int __init cmp_range(const void *x1, const void *x2)
+{
+ const struct res_range *r1 = x1;
+ const struct res_range *r2 = x2;
+ long start1, start2;
+
+ start1 = r1->start;
+ start2 = r2->start;
+
+ return start1 - start2;
+}
+
+struct var_mtrr_range_state {
+ unsigned long base_pfn;
+ unsigned long size_pfn;
+ mtrr_type type;
+};
+
+struct var_mtrr_range_state __initdata range_state[RANGE_NUM];
+static int __initdata debug_print;
+
+static int __init
+x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
+ unsigned long extra_remove_base,
+ unsigned long extra_remove_size)
+{
+ unsigned long i, base, size;
+ mtrr_type type;
+
+ for (i = 0; i < num_var_ranges; i++) {
+ type = range_state[i].type;
+ if (type != MTRR_TYPE_WRBACK)
+ continue;
+ base = range_state[i].base_pfn;
+ size = range_state[i].size_pfn;
+ nr_range = add_range_with_merge(range, nr_range, base,
+ base + size - 1);
+ }
+ if (debug_print) {
+ printk(KERN_DEBUG "After WB checking\n");
+ for (i = 0; i < nr_range; i++)
+ printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+ range[i].start, range[i].end + 1);
+ }
+
+ /* take out UC ranges */
+ for (i = 0; i < num_var_ranges; i++) {
+ type = range_state[i].type;
+ if (type != MTRR_TYPE_UNCACHABLE)
+ continue;
+ size = range_state[i].size_pfn;
+ if (!size)
+ continue;
+ base = range_state[i].base_pfn;
+ subtract_range(range, base, base + size - 1);
+ }
+ if (extra_remove_size)
+ subtract_range(range, extra_remove_base,
+ extra_remove_base + extra_remove_size - 1);
+
+ /* get new range num */
+ nr_range = 0;
+ for (i = 0; i < RANGE_NUM; i++) {
+ if (!range[i].end)
+ continue;
+ nr_range++;
+ }
+ if (debug_print) {
+ printk(KERN_DEBUG "After UC checking\n");
+ for (i = 0; i < nr_range; i++)
+ printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+ range[i].start, range[i].end + 1);
+ }
+
+ /* sort the ranges */
+ sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL);
+ if (debug_print) {
+ printk(KERN_DEBUG "After sorting\n");
+ for (i = 0; i < nr_range; i++)
+ printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n",
+ range[i].start, range[i].end + 1);
+ }
+
+ /* clear those is not used */
+ for (i = nr_range; i < RANGE_NUM; i++)
+ memset(&range[i], 0, sizeof(range[i]));
+
+ return nr_range;
+}
+
+static struct res_range __initdata range[RANGE_NUM];
+
+#ifdef CONFIG_MTRR_SANITIZER
+
+static unsigned long __init sum_ranges(struct res_range *range, int nr_range)
+{
+ unsigned long sum;
+ int i;
+
+ sum = 0;
+ for (i = 0; i < nr_range; i++)
+ sum += range[i].end + 1 - range[i].start;
+
+ return sum;
+}
+
+static int enable_mtrr_cleanup __initdata =
+ CONFIG_MTRR_SANITIZER_ENABLE_DEFAULT;
+
+static int __init disable_mtrr_cleanup_setup(char *str)
+{
+ if (enable_mtrr_cleanup != -1)
+ enable_mtrr_cleanup = 0;
+ return 0;
+}
+early_param("disable_mtrr_cleanup", disable_mtrr_cleanup_setup);
+
+static int __init enable_mtrr_cleanup_setup(char *str)
+{
+ if (enable_mtrr_cleanup != -1)
+ enable_mtrr_cleanup = 1;
+ return 0;
+}
+early_param("enble_mtrr_cleanup", enable_mtrr_cleanup_setup);
+
+struct var_mtrr_state {
+ unsigned long range_startk;
+ unsigned long range_sizek;
+ unsigned long chunk_sizek;
+ unsigned long gran_sizek;
+ unsigned int reg;
+};
+
+static void __init
+set_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
+ unsigned char type, unsigned int address_bits)
+{
+ u32 base_lo, base_hi, mask_lo, mask_hi;
+ u64 base, mask;
+
+ if (!sizek) {
+ fill_mtrr_var_range(reg, 0, 0, 0, 0);
+ return;
+ }
+
+ mask = (1ULL << address_bits) - 1;
+ mask &= ~((((u64)sizek) << 10) - 1);
+
+ base = ((u64)basek) << 10;
+
+ base |= type;
+ mask |= 0x800;
+
+ base_lo = base & ((1ULL<<32) - 1);
+ base_hi = base >> 32;
+
+ mask_lo = mask & ((1ULL<<32) - 1);
+ mask_hi = mask >> 32;
+
+ fill_mtrr_var_range(reg, base_lo, base_hi, mask_lo, mask_hi);
+}
+
+static void __init
+save_var_mtrr(unsigned int reg, unsigned long basek, unsigned long sizek,
+ unsigned char type)
+{
+ range_state[reg].base_pfn = basek >> (PAGE_SHIFT - 10);
+ range_state[reg].size_pfn = sizek >> (PAGE_SHIFT - 10);
+ range_state[reg].type = type;
+}
+
+static void __init
+set_var_mtrr_all(unsigned int address_bits)
+{
+ unsigned long basek, sizek;
+ unsigned char type;
+ unsigned int reg;
+
+ for (reg = 0; reg < num_var_ranges; reg++) {
+ basek = range_state[reg].base_pfn << (PAGE_SHIFT - 10);
+ sizek = range_state[reg].size_pfn << (PAGE_SHIFT - 10);
+ type = range_state[reg].type;
+
+ set_var_mtrr(reg, basek, sizek, type, address_bits);
+ }
+}
+
+static unsigned int __init
+range_to_mtrr(unsigned int reg, unsigned long range_startk,
+ unsigned long range_sizek, unsigned char type)
+{
+ if (!range_sizek || (reg >= num_var_ranges))
+ return reg;
+
+ while (range_sizek) {
+ unsigned long max_align, align;
+ unsigned long sizek;
+
+ /* Compute the maximum size I can make a range */
+ if (range_startk)
+ max_align = ffs(range_startk) - 1;
+ else
+ max_align = 32;
+ align = fls(range_sizek) - 1;
+ if (align > max_align)
+ align = max_align;
+
+ sizek = 1 << align;
+ if (debug_print)
+ printk(KERN_DEBUG "Setting variable MTRR %d, "
+ "base: %ldMB, range: %ldMB, type %s\n",
+ reg, range_startk >> 10, sizek >> 10,
+ (type == MTRR_TYPE_UNCACHABLE)?"UC":
+ ((type == MTRR_TYPE_WRBACK)?"WB":"Other")
+ );
+ save_var_mtrr(reg++, range_startk, sizek, type);
+ range_startk += sizek;
+ range_sizek -= sizek;
+ if (reg >= num_var_ranges)
+ break;
+ }
+ return reg;
+}
+
+static unsigned __init
+range_to_mtrr_with_hole(struct var_mtrr_state *state, unsigned long basek,
+ unsigned long sizek)
+{
+ unsigned long hole_basek, hole_sizek;
+ unsigned long second_basek, second_sizek;
+ unsigned long range0_basek, range0_sizek;
+ unsigned long range_basek, range_sizek;
+ unsigned long chunk_sizek;
+ unsigned long gran_sizek;
+
+ hole_basek = 0;
+ hole_sizek = 0;
+ second_basek = 0;
+ second_sizek = 0;
+ chunk_sizek = state->chunk_sizek;
+ gran_sizek = state->gran_sizek;
+
+ /* align with gran size, prevent small block used up MTRRs */
+ range_basek = ALIGN(state->range_startk, gran_sizek);
+ if ((range_basek > basek) && basek)
+ return second_sizek;
+ state->range_sizek -= (range_basek - state->range_startk);
+ range_sizek = ALIGN(state->range_sizek, gran_sizek);
+
+ while (range_sizek > state->range_sizek) {
+ range_sizek -= gran_sizek;
+ if (!range_sizek)
+ return 0;
+ }
+ state->range_sizek = range_sizek;
+
+ /* try to append some small hole */
+ range0_basek = state->range_startk;
+ range0_sizek = ALIGN(state->range_sizek, chunk_sizek);
+ if (range0_sizek == state->range_sizek) {
+ if (debug_print)
+ printk(KERN_DEBUG "rangeX: %016lx - %016lx\n",
+ range0_basek<<10,
+ (range0_basek + state->range_sizek)<<10);
+ state->reg = range_to_mtrr(state->reg, range0_basek,
+ state->range_sizek, MTRR_TYPE_WRBACK);
+ return 0;
+ }
+
+ range0_sizek -= chunk_sizek;
+ if (range0_sizek && sizek) {
+ while (range0_basek + range0_sizek > (basek + sizek)) {
+ range0_sizek -= chunk_sizek;
+ if (!range0_sizek)
+ break;
+ }
+ }
+
+ if (range0_sizek) {
+ if (debug_print)
+ printk(KERN_DEBUG "range0: %016lx - %016lx\n",
+ range0_basek<<10,
+ (range0_basek + range0_sizek)<<10);
+ state->reg = range_to_mtrr(state->reg, range0_basek,
+ range0_sizek, MTRR_TYPE_WRBACK);
+
+ }
+
+ range_basek = range0_basek + range0_sizek;
+ range_sizek = chunk_sizek;
+
+ if (range_basek + range_sizek > basek &&
+ range_basek + range_sizek <= (basek + sizek)) {
+ /* one hole */
+ second_basek = basek;
+ second_sizek = range_basek + range_sizek - basek;
+ }
+
+ /* if last piece, only could one hole near end */
+ if ((second_basek || !basek) &&
+ range_sizek - (state->range_sizek - range0_sizek) - second_sizek <
+ (chunk_sizek >> 1)) {
+ /*
+ * one hole in middle (second_sizek is 0) or at end
+ * (second_sizek is 0 )
+ */
+ hole_sizek = range_sizek - (state->range_sizek - range0_sizek)
+ - second_sizek;
+ hole_basek = range_basek + range_sizek - hole_sizek
+ - second_sizek;
+ } else {
+ /* fallback for big hole, or several holes */
+ range_sizek = state->range_sizek - range0_sizek;
+ second_basek = 0;
+ second_sizek = 0;
+ }
+
+ if (debug_print)
+ printk(KERN_DEBUG "range: %016lx - %016lx\n", range_basek<<10,
+ (range_basek + range_sizek)<<10);
+ state->reg = range_to_mtrr(state->reg, range_basek, range_sizek,
+ MTRR_TYPE_WRBACK);
+ if (hole_sizek) {
+ if (debug_print)
+ printk(KERN_DEBUG "hole: %016lx - %016lx\n",
+ hole_basek<<10, (hole_basek + hole_sizek)<<10);
+ state->reg = range_to_mtrr(state->reg, hole_basek, hole_sizek,
+ MTRR_TYPE_UNCACHABLE);
+
+ }
+
+ return second_sizek;
+}
+
+static void __init
+set_var_mtrr_range(struct var_mtrr_state *state, unsigned long base_pfn,
+ unsigned long size_pfn)
+{
+ unsigned long basek, sizek;
+ unsigned long second_sizek = 0;
+
+ if (state->reg >= num_var_ranges)
+ return;
+
+ basek = base_pfn << (PAGE_SHIFT - 10);
+ sizek = size_pfn << (PAGE_SHIFT - 10);
+
+ /* See if I can merge with the last range */
+ if ((basek <= 1024) ||
+ (state->range_startk + state->range_sizek == basek)) {
+ unsigned long endk = basek + sizek;
+ state->range_sizek = endk - state->range_startk;
+ return;
+ }
+ /* Write the range mtrrs */
+ if (state->range_sizek != 0)
+ second_sizek = range_to_mtrr_with_hole(state, basek, sizek);
+
+ /* Allocate an msr */
+ state->range_startk = basek + second_sizek;
+ state->range_sizek = sizek - second_sizek;
+}
+
+/* mininum size of mtrr block that can take hole */
+static u64 mtrr_chunk_size __initdata = (256ULL<<20);
+
+static int __init parse_mtrr_chunk_size_opt(char *p)
+{
+ if (!p)
+ return -EINVAL;
+ mtrr_chunk_size = memparse(p, &p);
+ return 0;
+}
+early_param("mtrr_chunk_size", parse_mtrr_chunk_size_opt);
+
+/* granity of mtrr of block */
+static u64 mtrr_gran_size __initdata;
+
+static int __init parse_mtrr_gran_size_opt(char *p)
+{
+ if (!p)
+ return -EINVAL;
+ mtrr_gran_size = memparse(p, &p);
+ return 0;
+}
+early_param("mtrr_gran_size", parse_mtrr_gran_size_opt);
+
+static int nr_mtrr_spare_reg __initdata =
+ CONFIG_MTRR_SANITIZER_SPARE_REG_NR_DEFAULT;
+
+static int __init parse_mtrr_spare_reg(char *arg)
+{
+ if (arg)
+ nr_mtrr_spare_reg = simple_strtoul(arg, NULL, 0);
+ return 0;
+}
+
+early_param("mtrr_spare_reg_nr", parse_mtrr_spare_reg);
+
+static int __init
+x86_setup_var_mtrrs(struct res_range *range, int nr_range,
+ u64 chunk_size, u64 gran_size)
+{
+ struct var_mtrr_state var_state;
+ int i;
+ int num_reg;
+
+ var_state.range_startk = 0;
+ var_state.range_sizek = 0;
+ var_state.reg = 0;
+ var_state.chunk_sizek = chunk_size >> 10;
+ var_state.gran_sizek = gran_size >> 10;
+
+ memset(range_state, 0, sizeof(range_state));
+
+ /* Write the range etc */
+ for (i = 0; i < nr_range; i++)
+ set_var_mtrr_range(&var_state, range[i].start,
+ range[i].end - range[i].start + 1);
+
+ /* Write the last range */
+ if (var_state.range_sizek != 0)
+ range_to_mtrr_with_hole(&var_state, 0, 0);
+
+ num_reg = var_state.reg;
+ /* Clear out the extra MTRR's */
+ while (var_state.reg < num_var_ranges) {
+ save_var_mtrr(var_state.reg, 0, 0, 0);
+ var_state.reg++;
+ }
+
+ return num_reg;
+}
+
+struct mtrr_cleanup_result {
+ unsigned long gran_sizek;
+ unsigned long chunk_sizek;
+ unsigned long lose_cover_sizek;
+ unsigned int num_reg;
+ int bad;
+};
+
+/*
+ * gran_size: 1M, 2M, ..., 2G
+ * chunk size: gran_size, ..., 4G
+ * so we need (2+13)*6
+ */
+#define NUM_RESULT 90
+#define PSHIFT (PAGE_SHIFT - 10)
+
+static struct mtrr_cleanup_result __initdata result[NUM_RESULT];
+static struct res_range __initdata range_new[RANGE_NUM];
+static unsigned long __initdata min_loss_pfn[RANGE_NUM];
+
+static int __init mtrr_cleanup(unsigned address_bits)
+{
+ unsigned long extra_remove_base, extra_remove_size;
+ unsigned long i, base, size, def, dummy;
+ mtrr_type type;
+ int nr_range, nr_range_new;
+ u64 chunk_size, gran_size;
+ unsigned long range_sums, range_sums_new;
+ int index_good;
+ int num_reg_good;
+
+ /* extra one for all 0 */
+ int num[MTRR_NUM_TYPES + 1];
+
+ if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
+ return 0;
+ rdmsr(MTRRdefType_MSR, def, dummy);
+ def &= 0xff;
+ if (def != MTRR_TYPE_UNCACHABLE)
+ return 0;
+
+ /* get it and store it aside */
+ memset(range_state, 0, sizeof(range_state));
+ for (i = 0; i < num_var_ranges; i++) {
+ mtrr_if->get(i, &base, &size, &type);
+ range_state[i].base_pfn = base;
+ range_state[i].size_pfn = size;
+ range_state[i].type = type;
+ }
+
+ /* check entries number */
+ memset(num, 0, sizeof(num));
+ for (i = 0; i < num_var_ranges; i++) {
+ type = range_state[i].type;
+ size = range_state[i].size_pfn;
+ if (type >= MTRR_NUM_TYPES)
+ continue;
+ if (!size)
+ type = MTRR_NUM_TYPES;
+ num[type]++;
+ }
+
+ /* check if we got UC entries */
+ if (!num[MTRR_TYPE_UNCACHABLE])
+ return 0;
+
+ /* check if we only had WB and UC */
+ if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] !=
+ num_var_ranges - num[MTRR_NUM_TYPES])
+ return 0;
+
+ memset(range, 0, sizeof(range));
+ extra_remove_size = 0;
+ if (mtrr_tom2) {
+ extra_remove_base = 1 << (32 - PAGE_SHIFT);
+ extra_remove_size =
+ (mtrr_tom2 >> PAGE_SHIFT) - extra_remove_base;
+ }
+ nr_range = x86_get_mtrr_mem_range(range, 0, extra_remove_base,
+ extra_remove_size);
+ range_sums = sum_ranges(range, nr_range);
+ printk(KERN_INFO "total RAM coverred: %ldM\n",
+ range_sums >> (20 - PAGE_SHIFT));
+
+ if (mtrr_chunk_size && mtrr_gran_size) {
+ int num_reg;
+
+ debug_print = 1;
+ /* convert ranges to var ranges state */
+ num_reg = x86_setup_var_mtrrs(range, nr_range, mtrr_chunk_size,
+ mtrr_gran_size);
+
+ /* we got new setting in range_state, check it */
+ memset(range_new, 0, sizeof(range_new));
+ nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
+ extra_remove_base,
+ extra_remove_size);
+ range_sums_new = sum_ranges(range_new, nr_range_new);
+
+ i = 0;
+ result[i].chunk_sizek = mtrr_chunk_size >> 10;
+ result[i].gran_sizek = mtrr_gran_size >> 10;
+ result[i].num_reg = num_reg;
+ if (range_sums < range_sums_new) {
+ result[i].lose_cover_sizek =
+ (range_sums_new - range_sums) << PSHIFT;
+ result[i].bad = 1;
+ } else
+ result[i].lose_cover_sizek =
+ (range_sums - range_sums_new) << PSHIFT;
+
+ printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t",
+ result[i].bad?"*BAD*":" ", result[i].gran_sizek >> 10,
+ result[i].chunk_sizek >> 10);
+ printk(KERN_CONT "num_reg: %d \tlose cover RAM: %s%ldM \n",
+ result[i].num_reg, result[i].bad?"-":"",
+ result[i].lose_cover_sizek >> 10);
+ if (!result[i].bad) {
+ set_var_mtrr_all(address_bits);
+ return 1;
+ }
+ printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
+ "will find optimal one\n");
+ debug_print = 0;
+ memset(result, 0, sizeof(result[0]));
+ }
+
+ i = 0;
+ memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn));
+ memset(result, 0, sizeof(result));
+ for (gran_size = (1ULL<<20); gran_size < (1ULL<<32); gran_size <<= 1) {
+ for (chunk_size = gran_size; chunk_size < (1ULL<<33);
+ chunk_size <<= 1) {
+ int num_reg;
+
+ if (debug_print)
+ printk(KERN_INFO
+ "\ngran_size: %lldM chunk_size_size: %lldM\n",
+ gran_size >> 20, chunk_size >> 20);
+ if (i >= NUM_RESULT)
+ continue;
+
+ /* convert ranges to var ranges state */
+ num_reg = x86_setup_var_mtrrs(range, nr_range,
+ chunk_size, gran_size);
+
+ /* we got new setting in range_state, check it */
+ memset(range_new, 0, sizeof(range_new));
+ nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
+ extra_remove_base, extra_remove_size);
+ range_sums_new = sum_ranges(range_new, nr_range_new);
+
+ result[i].chunk_sizek = chunk_size >> 10;
+ result[i].gran_sizek = gran_size >> 10;
+ result[i].num_reg = num_reg;
+ if (range_sums < range_sums_new) {
+ result[i].lose_cover_sizek =
+ (range_sums_new - range_sums) << PSHIFT;
+ result[i].bad = 1;
+ } else
+ result[i].lose_cover_sizek =
+ (range_sums - range_sums_new) << PSHIFT;
+
+ /* double check it */
+ if (!result[i].bad && !result[i].lose_cover_sizek) {
+ if (nr_range_new != nr_range ||
+ memcmp(range, range_new, sizeof(range)))
+ result[i].bad = 1;
+ }
+
+ if (!result[i].bad && (range_sums - range_sums_new <
+ min_loss_pfn[num_reg])) {
+ min_loss_pfn[num_reg] =
+ range_sums - range_sums_new;
+ }
+ i++;
+ }
+ }
+
+ /* print out all */
+ for (i = 0; i < NUM_RESULT; i++) {
+ printk(KERN_INFO "%sgran_size: %ldM \tchunk_size: %ldM \t",
+ result[i].bad?"*BAD* ":" ", result[i].gran_sizek >> 10,
+ result[i].chunk_sizek >> 10);
+ printk(KERN_CONT "num_reg: %d \tlose RAM: %s%ldM\n",
+ result[i].num_reg, result[i].bad?"-":"",
+ result[i].lose_cover_sizek >> 10);
+ }
+
+ /* try to find the optimal index */
+ if (nr_mtrr_spare_reg >= num_var_ranges)
+ nr_mtrr_spare_reg = num_var_ranges - 1;
+ num_reg_good = -1;
+ for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
+ if (!min_loss_pfn[i]) {
+ num_reg_good = i;
+ break;
+ }
+ }
+
+ index_good = -1;
+ if (num_reg_good != -1) {
+ for (i = 0; i < NUM_RESULT; i++) {
+ if (!result[i].bad &&
+ result[i].num_reg == num_reg_good &&
+ !result[i].lose_cover_sizek) {
+ index_good = i;
+ break;
+ }
+ }
+ }
+
+ if (index_good != -1) {
+ printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
+ i = index_good;
+ printk(KERN_INFO "gran_size: %ldM \tchunk_size: %ldM \t",
+ result[i].gran_sizek >> 10,
+ result[i].chunk_sizek >> 10);
+ printk(KERN_CONT "num_reg: %d \tlose RAM: %ldM\n",
+ result[i].num_reg,
+ result[i].lose_cover_sizek >> 10);
+ /* convert ranges to var ranges state */
+ chunk_size = result[i].chunk_sizek;
+ chunk_size <<= 10;
+ gran_size = result[i].gran_sizek;
+ gran_size <<= 10;
+ debug_print = 1;
+ x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
+ set_var_mtrr_all(address_bits);
+ return 1;
+ }
+
+ printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n");
+ printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n");
+
+ return 0;
+}
+#else
+static int __init mtrr_cleanup(unsigned address_bits)
+{
+ return 0;
+}
+#endif
+
+static int __initdata changed_by_mtrr_cleanup;
+
static int disable_mtrr_trim;
static int __init disable_mtrr_trim_setup(char *str)
return 0;
}
+static u64 __init real_trim_memory(unsigned long start_pfn,
+ unsigned long limit_pfn)
+{
+ u64 trim_start, trim_size;
+ trim_start = start_pfn;
+ trim_start <<= PAGE_SHIFT;
+ trim_size = limit_pfn;
+ trim_size <<= PAGE_SHIFT;
+ trim_size -= trim_start;
+
+ return e820_update_range(trim_start, trim_size, E820_RAM,
+ E820_RESERVED);
+}
/**
* mtrr_trim_uncached_memory - trim RAM not covered by MTRRs
* @end_pfn: ending page frame number
{
unsigned long i, base, size, highest_pfn = 0, def, dummy;
mtrr_type type;
- u64 trim_start, trim_size;
+ int nr_range;
+ u64 total_trim_size;
+ /* extra one for all 0 */
+ int num[MTRR_NUM_TYPES + 1];
/*
* Make sure we only trim uncachable memory on machines that
* support the Intel MTRR architecture:
if (def != MTRR_TYPE_UNCACHABLE)
return 0;
- if (amd_special_default_mtrr())
- return 0;
+ /* get it and store it aside */
+ memset(range_state, 0, sizeof(range_state));
+ for (i = 0; i < num_var_ranges; i++) {
+ mtrr_if->get(i, &base, &size, &type);
+ range_state[i].base_pfn = base;
+ range_state[i].size_pfn = size;
+ range_state[i].type = type;
+ }
/* Find highest cached pfn */
for (i = 0; i < num_var_ranges; i++) {
- mtrr_if->get(i, &base, &size, &type);
+ type = range_state[i].type;
if (type != MTRR_TYPE_WRBACK)
continue;
+ base = range_state[i].base_pfn;
+ size = range_state[i].size_pfn;
if (highest_pfn < base + size)
highest_pfn = base + size;
}
return 0;
}
- if (highest_pfn < end_pfn) {
+ /* check entries number */
+ memset(num, 0, sizeof(num));
+ for (i = 0; i < num_var_ranges; i++) {
+ type = range_state[i].type;
+ if (type >= MTRR_NUM_TYPES)
+ continue;
+ size = range_state[i].size_pfn;
+ if (!size)
+ type = MTRR_NUM_TYPES;
+ num[type]++;
+ }
+
+ /* no entry for WB? */
+ if (!num[MTRR_TYPE_WRBACK])
+ return 0;
+
+ /* check if we only had WB and UC */
+ if (num[MTRR_TYPE_WRBACK] + num[MTRR_TYPE_UNCACHABLE] !=
+ num_var_ranges - num[MTRR_NUM_TYPES])
+ return 0;
+
+ memset(range, 0, sizeof(range));
+ nr_range = 0;
+ if (mtrr_tom2) {
+ range[nr_range].start = (1ULL<<(32 - PAGE_SHIFT));
+ range[nr_range].end = (mtrr_tom2 >> PAGE_SHIFT) - 1;
+ if (highest_pfn < range[nr_range].end + 1)
+ highest_pfn = range[nr_range].end + 1;
+ nr_range++;
+ }
+ nr_range = x86_get_mtrr_mem_range(range, nr_range, 0, 0);
+
+ total_trim_size = 0;
+ /* check the head */
+ if (range[0].start)
+ total_trim_size += real_trim_memory(0, range[0].start);
+ /* check the holes */
+ for (i = 0; i < nr_range - 1; i++) {
+ if (range[i].end + 1 < range[i+1].start)
+ total_trim_size += real_trim_memory(range[i].end + 1,
+ range[i+1].start);
+ }
+ /* check the top */
+ i = nr_range - 1;
+ if (range[i].end + 1 < end_pfn)
+ total_trim_size += real_trim_memory(range[i].end + 1,
+ end_pfn);
+
+ if (total_trim_size) {
printk(KERN_WARNING "WARNING: BIOS bug: CPU MTRRs don't cover"
- " all of memory, losing %luMB of RAM.\n",
- (end_pfn - highest_pfn) >> (20 - PAGE_SHIFT));
+ " all of memory, losing %lluMB of RAM.\n",
+ total_trim_size >> 20);
- WARN_ON(1);
+ if (!changed_by_mtrr_cleanup)
+ WARN_ON(1);
printk(KERN_INFO "update e820 for mtrr\n");
- trim_start = highest_pfn;
- trim_start <<= PAGE_SHIFT;
- trim_size = end_pfn;
- trim_size <<= PAGE_SHIFT;
- trim_size -= trim_start;
- update_memory_range(trim_start, trim_size, E820_RAM,
- E820_RESERVED);
update_e820();
+
return 1;
}
*/
void __init mtrr_bp_init(void)
{
+ u32 phys_addr;
init_ifs();
+ phys_addr = 32;
+
if (cpu_has_mtrr) {
mtrr_if = &generic_mtrr_ops;
size_or_mask = 0xff000000; /* 36 bits */
size_and_mask = 0x00f00000;
+ phys_addr = 36;
/* This is an AMD specific MSR, but we assume(hope?) that
Intel will implement it to when they extend the address
bus of the Xeon. */
if (cpuid_eax(0x80000000) >= 0x80000008) {
- u32 phys_addr;
phys_addr = cpuid_eax(0x80000008) & 0xff;
/* CPUID workaround for Intel 0F33/0F34 CPU */
if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
don't support PAE */
size_or_mask = 0xfff00000; /* 32 bits */
size_and_mask = 0;
+ phys_addr = 32;
}
} else {
switch (boot_cpu_data.x86_vendor) {
if (mtrr_if) {
set_num_var_ranges();
init_table();
- if (use_intel())
+ if (use_intel()) {
get_mtrr_state();
+
+ if (mtrr_cleanup(phys_addr)) {
+ changed_by_mtrr_cleanup = 1;
+ mtrr_if->set_all();
+ }
+
+ }
}
}
*/
void mtrr_save_state(void)
{
- smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
+ smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1);
}
static int __init mtrr_init_finialize(void)
{
if (!mtrr_if)
return 0;
- if (use_intel())
- mtrr_state_warn();
- else {
+ if (use_intel()) {
+ if (!changed_by_mtrr_cleanup)
+ mtrr_state_warn();
+ } else {
/* The CPUs haven't MTRR and seem to not support SMP. They have
* specific drivers, we use a tricky method to support
* suspend/resume for them.
-/* local apic based NMI watchdog for various CPUs.
- This file also handles reservation of performance counters for coordination
- with other users (like oprofile).
-
- Note that these events normally don't tick when the CPU idles. This means
- the frequency varies with CPU load.
-
- Original code for K7/P6 written by Keith Owens */
+/*
+ * local apic based NMI watchdog for various CPUs.
+ *
+ * This file also handles reservation of performance counters for coordination
+ * with other users (like oprofile).
+ *
+ * Note that these events normally don't tick when the CPU idles. This means
+ * the frequency varies with CPU load.
+ *
+ * Original code for K7/P6 written by Keith Owens
+ *
+ */
#include <linux/percpu.h>
#include <linux/module.h>
static const struct wd_ops *wd_ops;
-/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
- * offset from MSR_P4_BSU_ESCR0. It will be the max for all platforms (for now)
+/*
+ * this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
+ * offset from MSR_P4_BSU_ESCR0.
+ *
+ * It will be the max for all platforms (for now)
*/
#define NMI_MAX_COUNTER_BITS 66
-/* perfctr_nmi_owner tracks the ownership of the perfctr registers:
+/*
+ * perfctr_nmi_owner tracks the ownership of the perfctr registers:
* evtsel_nmi_owner tracks the ownership of the event selection
* - different performance counters/ event selection may be reserved for
* different subsystems this reservation system just tries to coordinate
return 0;
}
-/* converts an msr to an appropriate reservation bit */
-/* returns the bit offset of the event selection register */
+/*
+ * converts an msr to an appropriate reservation bit
+ * returns the bit offset of the event selection register
+ */
static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
{
/* returns the bit offset of the event selection register */
return (!test_bit(counter, perfctr_nmi_owner));
}
+EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
int reserve_perfctr_nmi(unsigned int msr)
{
return 1;
return 0;
}
+EXPORT_SYMBOL(reserve_perfctr_nmi);
void release_perfctr_nmi(unsigned int msr)
{
clear_bit(counter, perfctr_nmi_owner);
}
+EXPORT_SYMBOL(release_perfctr_nmi);
int reserve_evntsel_nmi(unsigned int msr)
{
return 1;
return 0;
}
+EXPORT_SYMBOL(reserve_evntsel_nmi);
void release_evntsel_nmi(unsigned int msr)
{
clear_bit(counter, evntsel_nmi_owner);
}
-
-EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
-EXPORT_SYMBOL(reserve_perfctr_nmi);
-EXPORT_SYMBOL(release_perfctr_nmi);
-EXPORT_SYMBOL(reserve_evntsel_nmi);
EXPORT_SYMBOL(release_evntsel_nmi);
void disable_lapic_nmi_watchdog(void)
if (atomic_read(&nmi_active) <= 0)
return;
- on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);
+ on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
- wd_ops->unreserve();
+
+ if (wd_ops)
+ wd_ops->unreserve();
BUG_ON(atomic_read(&nmi_active) != 0);
}
return;
}
- on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
+ on_each_cpu(setup_apic_nmi_watchdog, NULL, 1);
touch_nmi_watchdog();
}
return retval;
}
-static void
-write_watchdog_counter(unsigned int perfctr_msr, const char *descr, unsigned nmi_hz)
+static void write_watchdog_counter(unsigned int perfctr_msr,
+ const char *descr, unsigned nmi_hz)
{
u64 count = (u64)cpu_khz * 1000;
}
static void write_watchdog_counter32(unsigned int perfctr_msr,
- const char *descr, unsigned nmi_hz)
+ const char *descr, unsigned nmi_hz)
{
u64 count = (u64)cpu_khz * 1000;
wrmsr(perfctr_msr, (u32)(-count), 0);
}
-/* AMD K7/K8/Family10h/Family11h support. AMD keeps this interface
- nicely stable so there is not much variety */
-
+/*
+ * AMD K7/K8/Family10h/Family11h support.
+ * AMD keeps this interface nicely stable so there is not much variety
+ */
#define K7_EVNTSEL_ENABLE (1 << 22)
#define K7_EVNTSEL_INT (1 << 20)
#define K7_EVNTSEL_OS (1 << 17)
wd->perfctr_msr = perfctr_msr;
wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = 0; //unused
+ wd->cccr_msr = 0; /* unused */
return 1;
}
}
static const struct wd_ops k7_wd_ops = {
- .reserve = single_msr_reserve,
- .unreserve = single_msr_unreserve,
- .setup = setup_k7_watchdog,
- .rearm = single_msr_rearm,
- .stop = single_msr_stop_watchdog,
- .perfctr = MSR_K7_PERFCTR0,
- .evntsel = MSR_K7_EVNTSEL0,
- .checkbit = 1ULL<<47,
+ .reserve = single_msr_reserve,
+ .unreserve = single_msr_unreserve,
+ .setup = setup_k7_watchdog,
+ .rearm = single_msr_rearm,
+ .stop = single_msr_stop_watchdog,
+ .perfctr = MSR_K7_PERFCTR0,
+ .evntsel = MSR_K7_EVNTSEL0,
+ .checkbit = 1ULL << 47,
};
-/* Intel Model 6 (PPro+,P2,P3,P-M,Core1) */
-
+/*
+ * Intel Model 6 (PPro+,P2,P3,P-M,Core1)
+ */
#define P6_EVNTSEL0_ENABLE (1 << 22)
#define P6_EVNTSEL_INT (1 << 20)
#define P6_EVNTSEL_OS (1 << 17)
wd->perfctr_msr = perfctr_msr;
wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = 0; //unused
+ wd->cccr_msr = 0; /* unused */
return 1;
}
static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
{
- /* P6 based Pentium M need to re-unmask
+ /*
+ * P6 based Pentium M need to re-unmask
* the apic vector but it doesn't hurt
* other P6 variant.
- * ArchPerfom/Core Duo also needs this */
+ * ArchPerfom/Core Duo also needs this
+ */
apic_write(APIC_LVTPC, APIC_DM_NMI);
+
/* P6/ARCH_PERFMON has 32 bit counter write */
write_watchdog_counter32(wd->perfctr_msr, NULL,nmi_hz);
}
static const struct wd_ops p6_wd_ops = {
- .reserve = single_msr_reserve,
- .unreserve = single_msr_unreserve,
- .setup = setup_p6_watchdog,
- .rearm = p6_rearm,
- .stop = single_msr_stop_watchdog,
- .perfctr = MSR_P6_PERFCTR0,
- .evntsel = MSR_P6_EVNTSEL0,
- .checkbit = 1ULL<<39,
+ .reserve = single_msr_reserve,
+ .unreserve = single_msr_unreserve,
+ .setup = setup_p6_watchdog,
+ .rearm = p6_rearm,
+ .stop = single_msr_stop_watchdog,
+ .perfctr = MSR_P6_PERFCTR0,
+ .evntsel = MSR_P6_EVNTSEL0,
+ .checkbit = 1ULL << 39,
};
-/* Intel P4 performance counters. By far the most complicated of all. */
-
-#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1<<7)
-#define P4_ESCR_EVENT_SELECT(N) ((N)<<25)
-#define P4_ESCR_OS (1<<3)
-#define P4_ESCR_USR (1<<2)
-#define P4_CCCR_OVF_PMI0 (1<<26)
-#define P4_CCCR_OVF_PMI1 (1<<27)
-#define P4_CCCR_THRESHOLD(N) ((N)<<20)
-#define P4_CCCR_COMPLEMENT (1<<19)
-#define P4_CCCR_COMPARE (1<<18)
-#define P4_CCCR_REQUIRED (3<<16)
-#define P4_CCCR_ESCR_SELECT(N) ((N)<<13)
-#define P4_CCCR_ENABLE (1<<12)
-#define P4_CCCR_OVF (1<<31)
-
-/* Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
- CRU_ESCR0 (with any non-null event selector) through a complemented
- max threshold. [IA32-Vol3, Section 14.9.9] */
+/*
+ * Intel P4 performance counters.
+ * By far the most complicated of all.
+ */
+#define MSR_P4_MISC_ENABLE_PERF_AVAIL (1 << 7)
+#define P4_ESCR_EVENT_SELECT(N) ((N) << 25)
+#define P4_ESCR_OS (1 << 3)
+#define P4_ESCR_USR (1 << 2)
+#define P4_CCCR_OVF_PMI0 (1 << 26)
+#define P4_CCCR_OVF_PMI1 (1 << 27)
+#define P4_CCCR_THRESHOLD(N) ((N) << 20)
+#define P4_CCCR_COMPLEMENT (1 << 19)
+#define P4_CCCR_COMPARE (1 << 18)
+#define P4_CCCR_REQUIRED (3 << 16)
+#define P4_CCCR_ESCR_SELECT(N) ((N) << 13)
+#define P4_CCCR_ENABLE (1 << 12)
+#define P4_CCCR_OVF (1 << 31)
+/*
+ * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
+ * CRU_ESCR0 (with any non-null event selector) through a complemented
+ * max threshold. [IA32-Vol3, Section 14.9.9]
+ */
static int setup_p4_watchdog(unsigned nmi_hz)
{
unsigned int perfctr_msr, evntsel_msr, cccr_msr;
#endif
ht_num = 0;
- /* performance counters are shared resources
+ /*
+ * performance counters are shared resources
* assign each hyperthread its own set
* (re-use the ESCR0 register, seems safe
* and keeps the cccr_val the same)
}
static const struct wd_ops p4_wd_ops = {
- .reserve = p4_reserve,
- .unreserve = p4_unreserve,
- .setup = setup_p4_watchdog,
- .rearm = p4_rearm,
- .stop = stop_p4_watchdog,
+ .reserve = p4_reserve,
+ .unreserve = p4_unreserve,
+ .setup = setup_p4_watchdog,
+ .rearm = p4_rearm,
+ .stop = stop_p4_watchdog,
/* RED-PEN this is wrong for the other sibling */
- .perfctr = MSR_P4_BPU_PERFCTR0,
- .evntsel = MSR_P4_BSU_ESCR0,
- .checkbit = 1ULL<<39,
+ .perfctr = MSR_P4_BPU_PERFCTR0,
+ .evntsel = MSR_P4_BSU_ESCR0,
+ .checkbit = 1ULL << 39,
};
-/* Watchdog using the Intel architected PerfMon. Used for Core2 and hopefully
- all future Intel CPUs. */
-
+/*
+ * Watchdog using the Intel architected PerfMon.
+ * Used for Core2 and hopefully all future Intel CPUs.
+ */
#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
wd->perfctr_msr = perfctr_msr;
wd->evntsel_msr = evntsel_msr;
- wd->cccr_msr = 0; //unused
+ wd->cccr_msr = 0; /* unused */
intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
return 1;
}
static struct wd_ops intel_arch_wd_ops __read_mostly = {
- .reserve = single_msr_reserve,
- .unreserve = single_msr_unreserve,
- .setup = setup_intel_arch_watchdog,
- .rearm = p6_rearm,
- .stop = single_msr_stop_watchdog,
- .perfctr = MSR_ARCH_PERFMON_PERFCTR1,
- .evntsel = MSR_ARCH_PERFMON_EVENTSEL1,
+ .reserve = single_msr_reserve,
+ .unreserve = single_msr_unreserve,
+ .setup = setup_intel_arch_watchdog,
+ .rearm = p6_rearm,
+ .stop = single_msr_stop_watchdog,
+ .perfctr = MSR_ARCH_PERFMON_PERFCTR1,
+ .evntsel = MSR_ARCH_PERFMON_EVENTSEL1,
};
static void probe_nmi_watchdog(void)
wd_ops = &k7_wd_ops;
break;
case X86_VENDOR_INTEL:
- /* Work around Core Duo (Yonah) errata AE49 where perfctr1
- doesn't have a working enable bit. */
+ /*
+ * Work around Core Duo (Yonah) errata AE49 where perfctr1
+ * doesn't have a working enable bit.
+ */
if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) {
intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0;
intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0;
}
switch (boot_cpu_data.x86) {
case 6:
- if (boot_cpu_data.x86_model > 0xd)
+ if (boot_cpu_data.x86_model > 13)
return;
wd_ops = &p6_wd_ops;
{
struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
u64 ctr;
+
rdmsrl(wd->perfctr_msr, ctr);
- if (ctr & wd_ops->checkbit) { /* perfctr still running? */
+ if (ctr & wd_ops->checkbit) /* perfctr still running? */
return 0;
- }
+
wd_ops->rearm(wd, nmi_hz);
return 1;
}
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/smp.h>
+#include <linux/smp_lock.h>
#include <linux/major.h>
#include <linux/fs.h>
#include <linux/smp_lock.h>
for (; count; count -= 16) {
cmd.eax = pos;
cmd.ecx = pos >> 32;
- smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1);
+ smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1);
if (copy_to_user(tmp, &cmd, 16))
return -EFAULT;
tmp += 16;
static int cpuid_open(struct inode *inode, struct file *file)
{
- unsigned int cpu = iminor(file->f_path.dentry->d_inode);
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-
- if (cpu >= NR_CPUS || !cpu_online(cpu))
- return -ENXIO; /* No such CPU */
+ unsigned int cpu;
+ struct cpuinfo_x86 *c;
+ int ret = 0;
+
+ lock_kernel();
+
+ cpu = iminor(file->f_path.dentry->d_inode);
+ if (cpu >= NR_CPUS || !cpu_online(cpu)) {
+ ret = -ENXIO; /* No such CPU */
+ goto out;
+ }
+ c = &cpu_data(cpu);
if (c->cpuid_level < 0)
- return -EIO; /* CPUID not supported */
-
- return 0;
+ ret = -EIO; /* CPUID not supported */
+out:
+ unlock_kernel();
+ return ret;
}
/*
#include <asm/page.h>
#include <asm/irqflags.h>
#include <asm/paravirt.h>
+#include <asm/ftrace.h>
.code64
+#ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(mcount)
+
+ subq $0x38, %rsp
+ movq %rax, (%rsp)
+ movq %rcx, 8(%rsp)
+ movq %rdx, 16(%rsp)
+ movq %rsi, 24(%rsp)
+ movq %rdi, 32(%rsp)
+ movq %r8, 40(%rsp)
+ movq %r9, 48(%rsp)
+
+ movq 0x38(%rsp), %rdi
+ subq $MCOUNT_INSN_SIZE, %rdi
+
+.globl mcount_call
+mcount_call:
+ call ftrace_stub
+
+ movq 48(%rsp), %r9
+ movq 40(%rsp), %r8
+ movq 32(%rsp), %rdi
+ movq 24(%rsp), %rsi
+ movq 16(%rsp), %rdx
+ movq 8(%rsp), %rcx
+ movq (%rsp), %rax
+ addq $0x38, %rsp
+
+ retq
+END(mcount)
+
+ENTRY(ftrace_caller)
+
+ /* taken from glibc */
+ subq $0x38, %rsp
+ movq %rax, (%rsp)
+ movq %rcx, 8(%rsp)
+ movq %rdx, 16(%rsp)
+ movq %rsi, 24(%rsp)
+ movq %rdi, 32(%rsp)
+ movq %r8, 40(%rsp)
+ movq %r9, 48(%rsp)
+
+ movq 0x38(%rsp), %rdi
+ movq 8(%rbp), %rsi
+ subq $MCOUNT_INSN_SIZE, %rdi
+
+.globl ftrace_call
+ftrace_call:
+ call ftrace_stub
+
+ movq 48(%rsp), %r9
+ movq 40(%rsp), %r8
+ movq 32(%rsp), %rdi
+ movq 24(%rsp), %rsi
+ movq 16(%rsp), %rdx
+ movq 8(%rsp), %rcx
+ movq (%rsp), %rax
+ addq $0x38, %rsp
+
+.globl ftrace_stub
+ftrace_stub:
+ retq
+END(ftrace_caller)
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+ENTRY(mcount)
+ cmpq $ftrace_stub, ftrace_trace_function
+ jnz trace
+.globl ftrace_stub
+ftrace_stub:
+ retq
+
+trace:
+ /* taken from glibc */
+ subq $0x38, %rsp
+ movq %rax, (%rsp)
+ movq %rcx, 8(%rsp)
+ movq %rdx, 16(%rsp)
+ movq %rsi, 24(%rsp)
+ movq %rdi, 32(%rsp)
+ movq %r8, 40(%rsp)
+ movq %r9, 48(%rsp)
+
+ movq 0x38(%rsp), %rdi
+ movq 8(%rbp), %rsi
+ subq $MCOUNT_INSN_SIZE, %rdi
+
+ call *ftrace_trace_function
+
+ movq 48(%rsp), %r9
+ movq 40(%rsp), %r8
+ movq 32(%rsp), %rdi
+ movq 24(%rsp), %rsi
+ movq 16(%rsp), %rdx
+ movq 8(%rsp), %rcx
+ movq (%rsp), %rax
+ addq $0x38, %rsp
+
+ jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FTRACE */
+
#ifndef CONFIG_PREEMPT
#define retint_kernel retint_restore_args
#endif
#ifdef CONFIG_PARAVIRT
-ENTRY(native_irq_enable_syscall_ret)
- movq %gs:pda_oldrsp,%rsp
+ENTRY(native_usergs_sysret64)
swapgs
sysretq
#endif /* CONFIG_PARAVIRT */
.macro FAKE_STACK_FRAME child_rip
/* push in order ss, rsp, eflags, cs, rip */
xorl %eax, %eax
- pushq %rax /* ss */
+ pushq $__KERNEL_DS /* ss */
CFI_ADJUST_CFA_OFFSET 8
/*CFI_REL_OFFSET ss,0*/
pushq %rax /* rsp */
CFI_ADJUST_CFA_OFFSET -4
call schedule_tail
GET_THREAD_INFO(%rcx)
- testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx)
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
jnz rff_trace
rff_action:
RESTORE_REST
testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread?
je int_ret_from_sys_call
- testl $_TIF_IA32,threadinfo_flags(%rcx)
+ testl $_TIF_IA32,TI_flags(%rcx)
jnz int_ret_from_sys_call
RESTORE_TOP_OF_STACK %rdi,ARGOFFSET
jmp ret_from_sys_call
movq %rcx,RIP-ARGOFFSET(%rsp)
CFI_REL_OFFSET rip,RIP-ARGOFFSET
GET_THREAD_INFO(%rcx)
- testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx)
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP), \
+ TI_flags(%rcx)
jnz tracesys
cmpq $__NR_syscall_max,%rax
ja badsys
GET_THREAD_INFO(%rcx)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- movl threadinfo_flags(%rcx),%edx
+ movl TI_flags(%rcx),%edx
andl %edi,%edx
jnz sysret_careful
CFI_REMEMBER_STATE
CFI_REGISTER rip,rcx
RESTORE_ARGS 0,-ARG_SKIP,1
/*CFI_REGISTER rflags,r11*/
- ENABLE_INTERRUPTS_SYSCALL_RET
+ movq %gs:pda_oldrsp, %rsp
+ USERGS_SYSRET64
CFI_RESTORE_STATE
/* Handle reschedules */
leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1
xorl %esi,%esi # oldset -> arg2
call ptregscall_common
-1: movl $_TIF_NEED_RESCHED,%edi
+1: movl $_TIF_WORK_MASK,%edi
/* Use IRET because user could have changed frame. This
works because ptregscall_common has called FIXUP_TOP_OF_STACK. */
DISABLE_INTERRUPTS(CLBR_NONE)
int_with_check:
LOCKDEP_SYS_EXIT_IRQ
GET_THREAD_INFO(%rcx)
- movl threadinfo_flags(%rcx),%edx
+ movl TI_flags(%rcx),%edx
andl %edi,%edx
jnz int_careful
- andl $~TS_COMPAT,threadinfo_status(%rcx)
+ andl $~TS_COMPAT,TI_status(%rcx)
jmp retint_swapgs
/* Either reschedule or signal or syscall exit tracking needed. */
movq %rsp,%rdi # &ptregs -> arg1
xorl %esi,%esi # oldset -> arg2
call do_notify_resume
-1: movl $_TIF_NEED_RESCHED,%edi
+1: movl $_TIF_WORK_MASK,%edi
int_restore_rest:
RESTORE_REST
DISABLE_INTERRUPTS(CLBR_NONE)
PTREGSCALL stub_clone, sys_clone, %r8
PTREGSCALL stub_fork, sys_fork, %rdi
PTREGSCALL stub_vfork, sys_vfork, %rdi
- PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx
PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
PTREGSCALL stub_iopl, sys_iopl, %rsi
movl $_TIF_WORK_MASK,%edi
retint_check:
LOCKDEP_SYS_EXIT_IRQ
- movl threadinfo_flags(%rcx),%edx
+ movl TI_flags(%rcx),%edx
andl %edi,%edx
CFI_REMEMBER_STATE
jnz retint_careful
RESTORE_REST
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- movl $_TIF_NEED_RESCHED,%edi
GET_THREAD_INFO(%rcx)
- jmp retint_check
+ jmp retint_with_reschedule
#ifdef CONFIG_PREEMPT
/* Returning to kernel space. Check if we need preemption */
/* rcx: threadinfo. interrupts off. */
ENTRY(retint_kernel)
- cmpl $0,threadinfo_preempt_count(%rcx)
+ cmpl $0,TI_preempt_count(%rcx)
jnz retint_restore_args
- bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx)
+ bt $TIF_NEED_RESCHED,TI_flags(%rcx)
jnc retint_restore_args
bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */
jnc retint_restore_args
ENTRY(call_function_interrupt)
apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
END(call_function_interrupt)
+ ENTRY(call_function_single_interrupt)
+ apicinterrupt CALL_FUNCTION_SINGLE_VECTOR,smp_call_function_single_interrupt
+ END(call_function_single_interrupt)
ENTRY(irq_move_cleanup_interrupt)
apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt
END(irq_move_cleanup_interrupt)
apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt
END(apic_timer_interrupt)
+ENTRY(uv_bau_message_intr1)
+ apicinterrupt 220,uv_bau_message_interrupt
+END(uv_bau_message_intr1)
+
ENTRY(error_interrupt)
apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt
END(error_interrupt)
*/
.macro zeroentry sym
INTR_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq $0 /* push error code/oldrax */
CFI_ADJUST_CFA_OFFSET 8
pushq %rax /* push real oldrax to the rdi slot */
.macro errorentry sym
XCPT_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq %rax
CFI_ADJUST_CFA_OFFSET 8
CFI_REL_OFFSET rax,0
jmp irq_return
paranoid_userspace\trace:
GET_THREAD_INFO(%rcx)
- movl threadinfo_flags(%rcx),%ebx
+ movl TI_flags(%rcx),%ebx
andl $_TIF_WORK_MASK,%ebx
jz paranoid_swapgs\trace
movq %rsp,%rdi /* &pt_regs */
testl %eax,%eax
jne retint_kernel
LOCKDEP_SYS_EXIT_IRQ
- movl threadinfo_flags(%rcx),%edx
+ movl TI_flags(%rcx),%edx
movl $_TIF_WORK_MASK,%edi
andl %edi,%edx
jnz retint_careful
iret run with kernel gs again, so don't set the user space flag.
B stepping K8s sometimes report an truncated RIP for IRET
exceptions returning to compat mode. Check for these here too. */
- leaq irq_return(%rip),%rbp
- cmpq %rbp,RIP(%rsp)
+ leaq irq_return(%rip),%rcx
+ cmpq %rcx,RIP(%rsp)
je error_swapgs
- movl %ebp,%ebp /* zero extend */
- cmpq %rbp,RIP(%rsp)
+ movl %ecx,%ecx /* zero extend */
+ cmpq %rcx,RIP(%rsp)
je error_swapgs
cmpq $gs_change,RIP(%rsp)
je error_swapgs
/* Reload gs selector with exception handling */
/* edi: new selector */
-ENTRY(load_gs_index)
+ENTRY(native_load_gs_index)
CFI_STARTPROC
pushf
CFI_ADJUST_CFA_OFFSET 8
CFI_ADJUST_CFA_OFFSET -8
ret
CFI_ENDPROC
-ENDPROC(load_gs_index)
+ENDPROC(native_load_gs_index)
.section __ex_table,"a"
.align 8
zeroentry do_coprocessor_segment_overrun
END(coprocessor_segment_overrun)
-ENTRY(reserved)
- zeroentry do_reserved
-END(reserved)
-
/* runs on exception stack */
ENTRY(double_fault)
XCPT_FRAME
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/sched.h>
+#include <linux/bootmem.h>
#include <linux/mc146818rtc.h>
#include <linux/compiler.h>
#include <linux/acpi.h>
static DEFINE_SPINLOCK(ioapic_lock);
static DEFINE_SPINLOCK(vector_lock);
-int timer_over_8254 __initdata = 1;
+int timer_through_8259 __initdata;
/*
* Is the SiS APIC rmw bug present ?
int nr_ioapic_registers[MAX_IO_APICS];
/* I/O APIC entries */
-struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
int nr_ioapics;
/* MP IRQ source entries */
-struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
/* # of MP IRQ source entries */
int mp_irq_entries;
+#if defined (CONFIG_MCA) || defined (CONFIG_EISA)
+int mp_bus_id_to_type[MAX_MP_BUSSES];
+#endif
+
+DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+
static int disable_timer_pin_1 __initdata;
/*
static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
{
return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
- + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK);
+ + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
}
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
}
}
-static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsigned long disable)
+static void __modify_IO_APIC_irq(unsigned int irq, unsigned long enable, unsigned long disable)
{
struct irq_pin_list *entry = irq_2_pin + irq;
unsigned int pin, reg;
}
/* mask = 1 */
-static void __mask_IO_APIC_irq (unsigned int irq)
+static void __mask_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00010000, 0);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED, 0);
}
/* mask = 0 */
-static void __unmask_IO_APIC_irq (unsigned int irq)
+static void __unmask_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0, 0x00010000);
+ __modify_IO_APIC_irq(irq, 0, IO_APIC_REDIR_MASKED);
}
/* mask = 1, trigger = 0 */
-static void __mask_and_edge_IO_APIC_irq (unsigned int irq)
+static void __mask_and_edge_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_MASKED,
+ IO_APIC_REDIR_LEVEL_TRIGGER);
}
/* mask = 0, trigger = 1 */
-static void __unmask_and_level_IO_APIC_irq (unsigned int irq)
+static void __unmask_and_level_IO_APIC_irq(unsigned int irq)
{
- __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000);
+ __modify_IO_APIC_irq(irq, IO_APIC_REDIR_LEVEL_TRIGGER,
+ IO_APIC_REDIR_MASKED);
}
-static void mask_IO_APIC_irq (unsigned int irq)
+static void mask_IO_APIC_irq(unsigned int irq)
{
unsigned long flags;
spin_unlock_irqrestore(&ioapic_lock, flags);
}
-static void unmask_IO_APIC_irq (unsigned int irq)
+static void unmask_IO_APIC_irq(unsigned int irq)
{
unsigned long flags;
static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
{
struct IO_APIC_route_entry entry;
-
+
/* Check delivery_mode to be sure we're not clearing an SMI pin */
entry = ioapic_read_entry(apic, pin);
if (entry.delivery_mode == dest_SMI)
ioapic_mask_entry(apic, pin);
}
-static void clear_IO_APIC (void)
+static void clear_IO_APIC(void)
{
int apic, pin;
struct irq_pin_list *entry = irq_2_pin + irq;
unsigned int apicid_value;
cpumask_t tmp;
-
+
cpus_and(tmp, cpumask, cpu_online_map);
if (cpus_empty(tmp))
tmp = TARGET_CPUS;
# include <linux/kernel_stat.h> /* kstat */
# include <linux/slab.h> /* kmalloc() */
# include <linux/timer.h>
-
+
#define IRQBALANCE_CHECK_ARCH -999
#define MAX_BALANCED_IRQ_INTERVAL (5*HZ)
#define MIN_BALANCED_IRQ_INTERVAL (HZ/2)
static long balanced_irq_interval __read_mostly = MAX_BALANCED_IRQ_INTERVAL;
static struct irq_cpu_info {
- unsigned long * last_irq;
- unsigned long * irq_delta;
+ unsigned long *last_irq;
+ unsigned long *irq_delta;
unsigned long irq;
} irq_cpu_data[NR_CPUS];
#define CPU_IRQ(cpu) (irq_cpu_data[cpu].irq)
-#define LAST_CPU_IRQ(cpu,irq) (irq_cpu_data[cpu].last_irq[irq])
-#define IRQ_DELTA(cpu,irq) (irq_cpu_data[cpu].irq_delta[irq])
+#define LAST_CPU_IRQ(cpu, irq) (irq_cpu_data[cpu].last_irq[irq])
+#define IRQ_DELTA(cpu, irq) (irq_cpu_data[cpu].irq_delta[irq])
#define IDLE_ENOUGH(cpu,now) \
(idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1))
if (cpu == -1)
cpu = NR_CPUS-1;
}
- } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu,allowed_mask) ||
- (search_idle && !IDLE_ENOUGH(cpu,now)));
+ } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu, allowed_mask) ||
+ (search_idle && !IDLE_ENOUGH(cpu, now)));
return cpu;
}
unsigned long now = jiffies;
cpumask_t allowed_mask;
unsigned int new_cpu;
-
+
if (irqbalance_disabled)
- return;
+ return;
cpus_and(allowed_mask, cpu_online_map, balance_irq_affinity[irq]);
new_cpu = move(cpu, allowed_mask, now, 1);
- if (cpu != new_cpu) {
+ if (cpu != new_cpu)
set_pending_irq(irq, cpumask_of_cpu(new_cpu));
- }
}
static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
if (!irq_desc[j].action)
continue;
/* Is it a significant load ? */
- if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i),j) <
+ if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) <
useful_load_threshold)
continue;
balance_irq(i, j);
}
}
balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
+ balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
return;
}
/* Is this an active IRQ or balancing disabled ? */
if (!irq_desc[j].action || irq_balancing_disabled(j))
continue;
- if ( package_index == i )
- IRQ_DELTA(package_index,j) = 0;
+ if (package_index == i)
+ IRQ_DELTA(package_index, j) = 0;
/* Determine the total count per processor per IRQ */
value_now = (unsigned long) kstat_cpu(i).irqs[j];
/* Determine the activity per processor per IRQ */
- delta = value_now - LAST_CPU_IRQ(i,j);
+ delta = value_now - LAST_CPU_IRQ(i, j);
/* Update last_cpu_irq[][] for the next time */
- LAST_CPU_IRQ(i,j) = value_now;
+ LAST_CPU_IRQ(i, j) = value_now;
/* Ignore IRQs whose rate is less than the clock */
if (delta < useful_load_threshold)
continue;
/* update the load for the processor or package total */
- IRQ_DELTA(package_index,j) += delta;
+ IRQ_DELTA(package_index, j) += delta;
/* Keep track of the higher numbered sibling as well */
if (i != package_index)
max_cpu_irq = ULONG_MAX;
tryanothercpu:
- /* Look for heaviest loaded processor.
+ /*
+ * Look for heaviest loaded processor.
* We may come back to get the next heaviest loaded processor.
* Skip processors with trivial loads.
*/
for_each_online_cpu(i) {
if (i != CPU_TO_PACKAGEINDEX(i))
continue;
- if (max_cpu_irq <= CPU_IRQ(i))
+ if (max_cpu_irq <= CPU_IRQ(i))
continue;
if (tmp_cpu_irq < CPU_IRQ(i)) {
tmp_cpu_irq = CPU_IRQ(i);
}
if (tmp_loaded == -1) {
- /* In the case of small number of heavy interrupt sources,
- * loading some of the cpus too much. We use Ingo's original
+ /*
+ * In the case of small number of heavy interrupt sources,
+ * loading some of the cpus too much. We use Ingo's original
* approach to rotate them around.
*/
if (!first_attempt && imbalance >= useful_load_threshold) {
}
goto not_worth_the_effort;
}
-
+
first_attempt = 0; /* heaviest search */
max_cpu_irq = tmp_cpu_irq; /* load */
max_loaded = tmp_loaded; /* processor */
imbalance = (max_cpu_irq - min_cpu_irq) / 2;
-
- /* if imbalance is less than approx 10% of max load, then
+
+ /*
+ * if imbalance is less than approx 10% of max load, then
* observe diminishing returns action. - quit
*/
if (imbalance < (max_cpu_irq >> 3))
/* Is this an active IRQ? */
if (!irq_desc[j].action)
continue;
- if (imbalance <= IRQ_DELTA(max_loaded,j))
+ if (imbalance <= IRQ_DELTA(max_loaded, j))
continue;
/* Try to find the IRQ that is closest to the imbalance
* without going over.
*/
- if (move_this_load < IRQ_DELTA(max_loaded,j)) {
- move_this_load = IRQ_DELTA(max_loaded,j);
+ if (move_this_load < IRQ_DELTA(max_loaded, j)) {
+ move_this_load = IRQ_DELTA(max_loaded, j);
selected_irq = j;
}
}
- if (selected_irq == -1) {
+ if (selected_irq == -1)
goto tryanothercpu;
- }
imbalance = move_this_load;
-
+
/* For physical_balance case, we accumulated both load
* values in the one of the siblings cpu_irq[],
* to use the same code for physical and logical processors
- * as much as possible.
+ * as much as possible.
*
* NOTE: the cpu_irq[] array holds the sum of the load for
* sibling A and sibling B in the slot for the lowest numbered
/* mark for change destination */
set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded));
- /* Since we made a change, come back sooner to
+ /* Since we made a change, come back sooner to
* check for more variation.
*/
balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
+ balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
return;
}
goto tryanotherirq;
* upward
*/
balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL,
- balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
+ balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
return;
}
cpumask_t tmp;
cpus_shift_right(tmp, cpu_online_map, 2);
- c = &boot_cpu_data;
+ c = &boot_cpu_data;
/* When not overwritten by the command line ask subarchitecture. */
if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH)
irqbalance_disabled = NO_BALANCE_IRQ;
if (irqbalance_disabled)
return 0;
-
+
/* disable irqbalance completely if there is only one processor online */
if (num_online_cpus() < 2) {
irqbalance_disabled = 1;
physical_balance = 1;
for_each_online_cpu(i) {
- irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
- irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+ irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+ irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
printk(KERN_ERR "balanced_irq_init: out of memory");
goto failed;
}
- memset(irq_cpu_data[i].irq_delta,0,sizeof(unsigned long) * NR_IRQS);
- memset(irq_cpu_data[i].last_irq,0,sizeof(unsigned long) * NR_IRQS);
}
-
+
printk(KERN_INFO "Starting balanced_irq\n");
if (!IS_ERR(kthread_run(balanced_irq, NULL, "kirqd")))
return 0;
int i;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_irqtype == type &&
- (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid ||
- mp_irqs[i].mpc_dstapic == MP_APIC_ALL) &&
- mp_irqs[i].mpc_dstirq == pin)
+ if (mp_irqs[i].mp_irqtype == type &&
+ (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
+ mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].mp_dstirq == pin)
return i;
return -1;
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mpc_irqtype == type) &&
- (mp_irqs[i].mpc_srcbusirq == irq))
+ (mp_irqs[i].mp_irqtype == type) &&
+ (mp_irqs[i].mp_srcbusirq == irq))
- return mp_irqs[i].mpc_dstirq;
+ return mp_irqs[i].mp_dstirq;
}
return -1;
}
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mpc_irqtype == type) &&
- (mp_irqs[i].mpc_srcbusirq == irq))
+ (mp_irqs[i].mp_irqtype == type) &&
+ (mp_irqs[i].mp_srcbusirq == irq))
break;
}
if (i < mp_irq_entries) {
int apic;
- for(apic = 0; apic < nr_ioapics; apic++) {
- if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
+ for (apic = 0; apic < nr_ioapics; apic++) {
+ if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
return apic;
}
}
apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, "
"slot:%d, pin:%d.\n", bus, slot, pin);
- if (mp_bus_id_to_pci_bus[bus] == -1) {
+ if (test_bit(bus, mp_bus_not_pci)) {
printk(KERN_WARNING "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
return -1;
}
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic ||
- mp_irqs[i].mpc_dstapic == MP_APIC_ALL)
+ if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
+ mp_irqs[i].mp_dstapic == MP_APIC_ALL)
break;
if (!test_bit(lbus, mp_bus_not_pci) &&
- !mp_irqs[i].mpc_irqtype &&
+ !mp_irqs[i].mp_irqtype &&
(bus == lbus) &&
- (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+ (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i, apic, mp_irqs[i].mp_dstirq);
if (!(apic || IO_APIC_IRQ(irq)))
continue;
- if (pin == (mp_irqs[i].mpc_srcbusirq & 3))
+ if (pin == (mp_irqs[i].mp_srcbusirq & 3))
return irq;
/*
* Use the first all-but-pin matching entry as a
EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
/*
- * This function currently is only a helper for the i386 smp boot process where
+ * This function currently is only a helper for the i386 smp boot process where
* we need to reprogram the ioredtbls to cater for the cpus which have come online
* so mask in all cases should simply be TARGET_CPUS
*/
* EISA conforming in the MP table, that means its trigger type must
* be read in from the ELCR */
-#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq))
+#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mp_srcbusirq))
#define default_EISA_polarity(idx) default_ISA_polarity(idx)
/* PCI interrupts are always polarity one level triggered,
static int MPBIOS_polarity(int idx)
{
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mpc_irqflag & 3)
+ switch (mp_irqs[idx].mp_irqflag & 3) {
+ case 0: /* conforms, ie. bus-type dependent polarity */
{
- case 0: /* conforms, ie. bus-type dependent polarity */
- {
- polarity = test_bit(bus, mp_bus_not_pci)?
- default_ISA_polarity(idx):
- default_PCI_polarity(idx);
- break;
- }
- case 1: /* high active */
- {
- polarity = 0;
- break;
- }
- case 2: /* reserved */
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- polarity = 1;
- break;
- }
- case 3: /* low active */
- {
- polarity = 1;
- break;
- }
- default: /* invalid */
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- polarity = 1;
- break;
- }
+ polarity = test_bit(bus, mp_bus_not_pci)?
+ default_ISA_polarity(idx):
+ default_PCI_polarity(idx);
+ break;
+ }
+ case 1: /* high active */
+ {
+ polarity = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
+ case 3: /* low active */
+ {
+ polarity = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ polarity = 1;
+ break;
+ }
}
return polarity;
}
static int MPBIOS_trigger(int idx)
{
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
int trigger;
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].mp_irqflag>>2) & 3) {
+ case 0: /* conforms, ie. bus-type dependent */
{
- case 0: /* conforms, ie. bus-type dependent */
- {
- trigger = test_bit(bus, mp_bus_not_pci)?
- default_ISA_trigger(idx):
- default_PCI_trigger(idx);
+ trigger = test_bit(bus, mp_bus_not_pci)?
+ default_ISA_trigger(idx):
+ default_PCI_trigger(idx);
#if defined(CONFIG_EISA) || defined(CONFIG_MCA)
- switch (mp_bus_id_to_type[bus])
- {
- case MP_BUS_ISA: /* ISA pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_EISA: /* EISA pin */
- {
- trigger = default_EISA_trigger(idx);
- break;
- }
- case MP_BUS_PCI: /* PCI pin */
- {
- /* set before the switch */
- break;
- }
- case MP_BUS_MCA: /* MCA pin */
- {
- trigger = default_MCA_trigger(idx);
- break;
- }
- default:
- {
- printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 1;
- break;
- }
- }
-#endif
+ switch (mp_bus_id_to_type[bus]) {
+ case MP_BUS_ISA: /* ISA pin */
+ {
+ /* set before the switch */
break;
}
- case 1: /* edge */
+ case MP_BUS_EISA: /* EISA pin */
{
- trigger = 0;
+ trigger = default_EISA_trigger(idx);
break;
}
- case 2: /* reserved */
+ case MP_BUS_PCI: /* PCI pin */
{
- printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 1;
+ /* set before the switch */
break;
}
- case 3: /* level */
+ case MP_BUS_MCA: /* MCA pin */
{
- trigger = 1;
+ trigger = default_MCA_trigger(idx);
break;
}
- default: /* invalid */
+ default:
{
printk(KERN_WARNING "broken BIOS!!\n");
- trigger = 0;
+ trigger = 1;
break;
}
}
+#endif
+ break;
+ }
+ case 1: /* edge */
+ {
+ trigger = 0;
+ break;
+ }
+ case 2: /* reserved */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 1;
+ break;
+ }
+ case 3: /* level */
+ {
+ trigger = 1;
+ break;
+ }
+ default: /* invalid */
+ {
+ printk(KERN_WARNING "broken BIOS!!\n");
+ trigger = 0;
+ break;
+ }
+ }
return trigger;
}
static int pin_2_irq(int idx, int apic, int pin)
{
int irq, i;
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
/*
* Debugging check, we are in big trouble if this message pops up!
*/
- if (mp_irqs[idx].mpc_dstirq != pin)
+ if (mp_irqs[idx].mp_dstirq != pin)
printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
if (test_bit(bus, mp_bus_not_pci))
- irq = mp_irqs[idx].mpc_srcbusirq;
+ irq = mp_irqs[idx].mp_srcbusirq;
else {
/*
* PCI IRQs are mapped in order
for (apic = 0; apic < nr_ioapics; apic++) {
for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
- idx = find_irq_entry(apic,pin,mp_INT);
- if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin)))
+ idx = find_irq_entry(apic, pin, mp_INT);
+ if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
return irq_trigger(idx);
}
}
static int __assign_irq_vector(int irq)
{
- static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+ static int current_vector = FIRST_DEVICE_VECTOR, current_offset;
int vector, offset;
BUG_ON((unsigned)irq >= NR_IRQ_VECTORS);
offset = current_offset;
next:
vector += 8;
- if (vector >= FIRST_SYSTEM_VECTOR) {
+ if (vector >= first_system_vector) {
offset = (offset + 1) % 8;
vector = FIRST_DEVICE_VECTOR + offset;
}
return vector;
}
+
+void setup_vector_irq(int cpu)
+{
+}
+
static struct irq_chip ioapic_chip;
#define IOAPIC_AUTO -1
/*
* add it to the IO-APIC irq-routing table:
*/
- memset(&entry,0,sizeof(entry));
+ memset(&entry, 0, sizeof(entry));
entry.delivery_mode = INT_DELIVERY_MODE;
entry.dest_mode = INT_DEST_MODE;
entry.mask = 0; /* enable IRQ */
- entry.dest.logical.logical_dest =
+ entry.dest.logical.logical_dest =
cpu_mask_to_apicid(TARGET_CPUS);
- idx = find_irq_entry(apic,pin,mp_INT);
+ idx = find_irq_entry(apic, pin, mp_INT);
if (idx == -1) {
if (first_notcon) {
apic_printk(APIC_VERBOSE, KERN_DEBUG
" IO-APIC (apicid-pin) %d-%d",
- mp_ioapics[apic].mpc_apicid,
+ mp_ioapics[apic].mp_apicid,
pin);
first_notcon = 0;
} else
apic_printk(APIC_VERBOSE, ", %d-%d",
- mp_ioapics[apic].mpc_apicid, pin);
+ mp_ioapics[apic].mp_apicid, pin);
continue;
}
vector = assign_irq_vector(irq);
entry.vector = vector;
ioapic_register_intr(irq, vector, IOAPIC_AUTO);
-
+
if (!apic && (irq < 16))
disable_8259A_irq(irq);
}
}
/*
- * Set up the 8259A-master output pin:
+ * Set up the timer pin, possibly with the 8259A-master behind.
*/
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+ int vector)
{
struct IO_APIC_route_entry entry;
- memset(&entry,0,sizeof(entry));
-
- disable_8259A_irq(0);
-
- /* mask LVT0 */
- apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
+ memset(&entry, 0, sizeof(entry));
/*
* We use logical delivery to get the timer IRQ
* to the first CPU.
*/
entry.dest_mode = INT_DEST_MODE;
- entry.mask = 0; /* unmask IRQ now */
+ entry.mask = 1; /* mask IRQ now */
entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
entry.delivery_mode = INT_DELIVERY_MODE;
entry.polarity = 0;
/*
* The timer IRQ doesn't have to know that behind the
- * scene we have a 8259A-master in AEOI mode ...
+ * scene we may have a 8259A-master in AEOI mode ...
*/
- irq_desc[0].chip = &ioapic_chip;
- set_irq_handler(0, handle_edge_irq);
+ ioapic_register_intr(0, vector, IOAPIC_EDGE);
/*
* Add it to the IO-APIC irq-routing table:
*/
ioapic_write_entry(apic, pin, entry);
-
- enable_8259A_irq(0);
}
void __init print_IO_APIC(void)
if (apic_verbosity == APIC_QUIET)
return;
- printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
+ printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (i = 0; i < nr_ioapics; i++)
printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
- mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
+ mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
/*
* We are a bit conservative about what we expect. We have to
reg_03.raw = io_apic_read(apic, 3);
spin_unlock_irqrestore(&ioapic_lock, flags);
- printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type);
#if 0
-static void print_APIC_bitfield (int base)
+static void print_APIC_bitfield(int base)
{
unsigned int v;
int i, j;
}
}
-void /*__init*/ print_local_APIC(void * dummy)
+void /*__init*/ print_local_APIC(void *dummy)
{
unsigned int v, ver, maxlvt;
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v,
GET_APIC_ID(read_apic_id()));
v = apic_read(APIC_LVR);
printk("\n");
}
-void print_all_local_APICs (void)
+void print_all_local_APICs(void)
{
- on_each_cpu(print_local_APIC, NULL, 1, 1);
+ on_each_cpu(print_local_APIC, NULL, 1);
}
void /*__init*/ print_PIC(void)
v = inb(0xa0) << 8 | inb(0x20);
printk(KERN_DEBUG "... PIC IRR: %04x\n", v);
- outb(0x0b,0xa0);
- outb(0x0b,0x20);
+ outb(0x0b, 0xa0);
+ outb(0x0b, 0x20);
v = inb(0xa0) << 8 | inb(0x20);
- outb(0x0a,0xa0);
- outb(0x0a,0x20);
+ outb(0x0a, 0xa0);
+ outb(0x0a, 0x20);
spin_unlock_irqrestore(&i8259A_lock, flags);
spin_unlock_irqrestore(&ioapic_lock, flags);
nr_ioapic_registers[apic] = reg_01.bits.entries+1;
}
- for(apic = 0; apic < nr_ioapics; apic++) {
+ for (apic = 0; apic < nr_ioapics; apic++) {
int pin;
/* See if any of the pins is in ExtINT mode */
for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
* by Matt Domsch <Matt_Domsch@dell.com> Tue Dec 21 12:25:05 CST 1999
*/
-#ifndef CONFIG_X86_NUMAQ
static void __init setup_ioapic_ids_from_mpc(void)
{
union IO_APIC_reg_00 reg_00;
unsigned char old_id;
unsigned long flags;
+#ifdef CONFIG_X86_NUMAQ
+ if (found_numaq)
+ return;
+#endif
+
/*
* Don't check I/O APIC IDs for xAPIC systems. They have
* no meaning without the serial APIC bus.
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
-
- old_id = mp_ioapics[apic].mpc_apicid;
- if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) {
+ old_id = mp_ioapics[apic].mp_apicid;
+
+ if (mp_ioapics[apic].mp_apicid >= get_physical_broadcast()) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
- apic, mp_ioapics[apic].mpc_apicid);
+ apic, mp_ioapics[apic].mp_apicid);
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
reg_00.bits.ID);
- mp_ioapics[apic].mpc_apicid = reg_00.bits.ID;
+ mp_ioapics[apic].mp_apicid = reg_00.bits.ID;
}
/*
* 'stuck on smp_invalidate_needed IPI wait' messages.
*/
if (check_apicid_used(phys_id_present_map,
- mp_ioapics[apic].mpc_apicid)) {
+ mp_ioapics[apic].mp_apicid)) {
printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
- apic, mp_ioapics[apic].mpc_apicid);
+ apic, mp_ioapics[apic].mp_apicid);
for (i = 0; i < get_physical_broadcast(); i++)
if (!physid_isset(i, phys_id_present_map))
break;
printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
i);
physid_set(i, phys_id_present_map);
- mp_ioapics[apic].mpc_apicid = i;
+ mp_ioapics[apic].mp_apicid = i;
} else {
physid_mask_t tmp;
- tmp = apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid);
+ tmp = apicid_to_cpu_present(mp_ioapics[apic].mp_apicid);
apic_printk(APIC_VERBOSE, "Setting %d in the "
"phys_id_present_map\n",
- mp_ioapics[apic].mpc_apicid);
+ mp_ioapics[apic].mp_apicid);
physids_or(phys_id_present_map, phys_id_present_map, tmp);
}
* We need to adjust the IRQ routing table
* if the ID changed.
*/
- if (old_id != mp_ioapics[apic].mpc_apicid)
+ if (old_id != mp_ioapics[apic].mp_apicid)
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_dstapic == old_id)
- mp_irqs[i].mpc_dstapic
- = mp_ioapics[apic].mpc_apicid;
+ if (mp_irqs[i].mp_dstapic == old_id)
+ mp_irqs[i].mp_dstapic
+ = mp_ioapics[apic].mp_apicid;
/*
* Read the right value from the MPC table and
* write it into the ID register.
- */
+ */
apic_printk(APIC_VERBOSE, KERN_INFO
"...changing IO-APIC physical APIC ID to %d ...",
- mp_ioapics[apic].mpc_apicid);
+ mp_ioapics[apic].mp_apicid);
- reg_00.bits.ID = mp_ioapics[apic].mpc_apicid;
+ reg_00.bits.ID = mp_ioapics[apic].mp_apicid;
spin_lock_irqsave(&ioapic_lock, flags);
io_apic_write(apic, 0, reg_00.raw);
spin_unlock_irqrestore(&ioapic_lock, flags);
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(apic, 0);
spin_unlock_irqrestore(&ioapic_lock, flags);
- if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid)
+ if (reg_00.bits.ID != mp_ioapics[apic].mp_apicid)
printk("could not set ID!\n");
else
apic_printk(APIC_VERBOSE, " ok.\n");
}
}
-#else
-static void __init setup_ioapic_ids_from_mpc(void) { }
-#endif
int no_timer_check __initdata;
* The local APIC irq-chip implementation:
*/
-static void ack_apic(unsigned int irq)
+static void ack_lapic_irq(unsigned int irq)
{
ack_APIC_irq();
}
-static void mask_lapic_irq (unsigned int irq)
+static void mask_lapic_irq(unsigned int irq)
{
unsigned long v;
apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED);
}
-static void unmask_lapic_irq (unsigned int irq)
+static void unmask_lapic_irq(unsigned int irq)
{
unsigned long v;
}
static struct irq_chip lapic_chip __read_mostly = {
- .name = "local-APIC-edge",
+ .name = "local-APIC",
.mask = mask_lapic_irq,
.unmask = unmask_lapic_irq,
- .eoi = ack_apic,
+ .ack = ack_lapic_irq,
};
+static void lapic_register_intr(int irq, int vector)
+{
+ irq_desc[irq].status &= ~IRQ_LEVEL;
+ set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+ "edge");
+ set_intr_gate(vector, interrupt[irq]);
+}
+
static void __init setup_nmi(void)
{
/*
- * Dirty trick to enable the NMI watchdog ...
+ * Dirty trick to enable the NMI watchdog ...
* We put the 8259A master into AEOI mode and
* unmask on all local APICs LVT0 as NMI.
*
* The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
* is from Maciej W. Rozycki - so we do not have to EOI from
* the NMI handler or the timer interrupt.
- */
+ */
apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
enable_NMI_through_LVT0();
static inline void __init check_timer(void)
{
int apic1, pin1, apic2, pin2;
+ int no_pin1 = 0;
int vector;
+ unsigned int ver;
unsigned long flags;
local_irq_save(flags);
+ ver = apic_read(APIC_LVR);
+ ver = GET_APIC_VERSION(ver);
+
/*
* get/set the timer IRQ vector:
*/
set_intr_gate(vector, interrupt[0]);
/*
- * Subtle, code in do_timer_interrupt() expects an AEOI
- * mode for the 8259A whenever interrupts are routed
- * through I/O APICs. Also IRQ0 has to be enabled in
- * the 8259A which implies the virtual wire has to be
- * disabled in the local APIC.
+ * As IRQ0 is to be enabled in the 8259A, the virtual
+ * wire has to be disabled in the local APIC. Also
+ * timer interrupts need to be acknowledged manually in
+ * the 8259A for the i82489DX when using the NMI
+ * watchdog as that APIC treats NMIs as level-triggered.
+ * The AEOI mode will finish them in the 8259A
+ * automatically.
*/
apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
- timer_ack = 1;
- if (timer_over_8254 > 0)
- enable_8259A_irq(0);
+ 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);
printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
vector, apic1, pin1, apic2, pin2);
+ /*
+ * Some BIOS writers are clueless and report the ExtINTA
+ * I/O APIC input from the cascaded 8259A as the timer
+ * interrupt input. So just in case, if only one pin
+ * was found above, try it both directly and through the
+ * 8259A.
+ */
+ if (pin1 == -1) {
+ pin1 = pin2;
+ apic1 = apic2;
+ no_pin1 = 1;
+ } else if (pin2 == -1) {
+ pin2 = pin1;
+ apic2 = apic1;
+ }
+
if (pin1 != -1) {
/*
* Ok, does IRQ0 through the IOAPIC work?
*/
+ if (no_pin1) {
+ add_pin_to_irq(0, apic1, pin1);
+ setup_timer_IRQ0_pin(apic1, pin1, vector);
+ }
unmask_IO_APIC_irq(0);
if (timer_irq_works()) {
if (nmi_watchdog == NMI_IO_APIC) {
- disable_8259A_irq(0);
setup_nmi();
enable_8259A_irq(0);
}
goto out;
}
clear_IO_APIC_pin(apic1, pin1);
- printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to "
- "IO-APIC\n");
- }
+ if (!no_pin1)
+ printk(KERN_ERR "..MP-BIOS bug: "
+ "8254 timer not connected to IO-APIC\n");
- printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... ");
- if (pin2 != -1) {
+ printk(KERN_INFO "...trying to set up timer (IRQ0) "
+ "through the 8259A ... ");
printk("\n..... (found pin %d) ...", pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
- setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
+ replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+ setup_timer_IRQ0_pin(apic2, pin2, vector);
+ unmask_IO_APIC_irq(0);
+ enable_8259A_irq(0);
if (timer_irq_works()) {
printk("works.\n");
- if (pin1 != -1)
- replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
- else
- add_pin_to_irq(0, apic2, pin2);
+ timer_through_8259 = 1;
if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
setup_nmi();
+ enable_8259A_irq(0);
}
goto out;
}
/*
* Cleanup, just in case ...
*/
+ disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
+ printk(" failed.\n");
}
- printk(" failed.\n");
if (nmi_watchdog == NMI_IO_APIC) {
printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
- nmi_watchdog = 0;
+ nmi_watchdog = NMI_NONE;
}
+ timer_ack = 0;
printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
- disable_8259A_irq(0);
- set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
- "fasteoi");
+ lapic_register_intr(0, vector);
apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */
enable_8259A_irq(0);
printk(" works.\n");
goto out;
}
+ disable_8259A_irq(0);
apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
printk(" failed.\n");
printk(KERN_INFO "...trying to set up timer as ExtINT IRQ...");
- timer_ack = 0;
init_8259A(0);
make_8259A_irq(0);
apic_write_around(APIC_LVT0, APIC_DM_EXTINT);
}
/*
- *
- * IRQ's that are handled by the PIC in the MPS IOAPIC case.
- * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
- * Linux doesn't really care, as it's not actually used
- * for any interrupt handling anyway.
+ * Traditionally ISA IRQ2 is the cascade IRQ, and is not available
+ * to devices. However there may be an I/O APIC pin available for
+ * this interrupt regardless. The pin may be left unconnected, but
+ * typically it will be reused as an ExtINT cascade interrupt for
+ * the master 8259A. In the MPS case such a pin will normally be
+ * reported as an ExtINT interrupt in the MP table. With ACPI
+ * there is no provision for ExtINT interrupts, and in the absence
+ * of an override it would be treated as an ordinary ISA I/O APIC
+ * interrupt, that is edge-triggered and unmasked by default. We
+ * used to do this, but it caused problems on some systems because
+ * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using
+ * the same ExtINT cascade interrupt to drive the local APIC of the
+ * bootstrap processor. Therefore we refrain from routing IRQ2 to
+ * the I/O APIC in all cases now. No actual device should request
+ * it anyway. --macro
*/
#define PIC_IRQS (1 << PIC_CASCADE_IR)
int i;
/* Reserve all the system vectors. */
- for (i = FIRST_SYSTEM_VECTOR; i < NR_VECTORS; i++)
+ for (i = first_system_vector; i < NR_VECTORS; i++)
set_bit(i, used_vectors);
enable_IO_APIC();
- if (acpi_ioapic)
- io_apic_irqs = ~0; /* all IRQs go through IOAPIC */
- else
- io_apic_irqs = ~PIC_IRQS;
+ io_apic_irqs = ~PIC_IRQS;
printk("ENABLING IO-APIC IRQs\n");
print_IO_APIC();
}
-static int __init setup_disable_8254_timer(char *s)
-{
- timer_over_8254 = -1;
- return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
- timer_over_8254 = 2;
- return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
/*
* Called after all the initialization is done. If we didnt find any
* APIC bugs then we can allow the modify fast path
*/
-
+
static int __init io_apic_bug_finalize(void)
{
- if(sis_apic_bug == -1)
+ if (sis_apic_bug == -1)
sis_apic_bug = 0;
return 0;
}
struct sys_device dev;
struct IO_APIC_route_entry entry[0];
};
-static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+static struct sysfs_ioapic_data *mp_ioapic_data[MAX_IO_APICS];
static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
{
struct IO_APIC_route_entry *entry;
struct sysfs_ioapic_data *data;
int i;
-
+
data = container_of(dev, struct sysfs_ioapic_data, dev);
entry = data->entry;
- for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
entry[i] = ioapic_read_entry(dev->id, i);
return 0;
unsigned long flags;
union IO_APIC_reg_00 reg_00;
int i;
-
+
data = container_of(dev, struct sysfs_ioapic_data, dev);
entry = data->entry;
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid;
+ if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
- for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
+ for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
ioapic_write_entry(dev->id, i, entry[i]);
return 0;
static int __init ioapic_init_sysfs(void)
{
- struct sys_device * dev;
+ struct sys_device *dev;
int i, size, error = 0;
error = sysdev_class_register(&ioapic_sysdev_class);
if (error)
return error;
- for (i = 0; i < nr_ioapics; i++ ) {
- size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+ for (i = 0; i < nr_ioapics; i++) {
+ size = sizeof(struct sys_device) + nr_ioapic_registers[i]
* sizeof(struct IO_APIC_route_entry);
- mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+ mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
if (!mp_ioapic_data[i]) {
printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
continue;
}
- memset(mp_ioapic_data[i], 0, size);
dev = &mp_ioapic_data[i]->dev;
- dev->id = i;
+ dev->id = i;
dev->cls = &ioapic_sysdev_class;
error = sysdev_register(dev);
if (error) {
msg->address_lo =
MSI_ADDR_BASE_LO |
((INT_DEST_MODE == 0) ?
- MSI_ADDR_DEST_MODE_PHYSICAL:
+MSI_ADDR_DEST_MODE_PHYSICAL:
MSI_ADDR_DEST_MODE_LOGICAL) |
((INT_DELIVERY_MODE != dest_LowestPrio) ?
MSI_ADDR_REDIRECTION_CPU:
MSI_DATA_TRIGGER_EDGE |
MSI_DATA_LEVEL_ASSERT |
((INT_DELIVERY_MODE != dest_LowestPrio) ?
- MSI_DATA_DELIVERY_FIXED:
+MSI_DATA_DELIVERY_FIXED:
MSI_DATA_DELIVERY_LOWPRI) |
MSI_DATA_VECTOR(vector);
}
#endif /* CONFIG_HT_IRQ */
/* --------------------------------------------------------------------------
- ACPI-based IOAPIC Configuration
+ ACPI-based IOAPIC Configuration
-------------------------------------------------------------------------- */
#ifdef CONFIG_ACPI
-int __init io_apic_get_unique_id (int ioapic, int apic_id)
+int __init io_apic_get_unique_id(int ioapic, int apic_id)
{
union IO_APIC_reg_00 reg_00;
static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
int i = 0;
/*
- * The P4 platform supports up to 256 APIC IDs on two separate APIC
- * buses (one for LAPICs, one for IOAPICs), where predecessors only
+ * The P4 platform supports up to 256 APIC IDs on two separate APIC
+ * buses (one for LAPICs, one for IOAPICs), where predecessors only
* supports up to 16 on one shared APIC bus.
- *
+ *
* TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full
* advantage of new APIC bus architecture.
*/
}
/*
- * Every APIC in a system must have a unique ID or we get lots of nice
+ * Every APIC in a system must have a unique ID or we get lots of nice
* 'stuck on smp_invalidate_needed IPI wait' messages.
*/
if (check_apicid_used(apic_id_map, apic_id)) {
"trying %d\n", ioapic, apic_id, i);
apic_id = i;
- }
+ }
tmp = apicid_to_cpu_present(apic_id);
physids_or(apic_id_map, apic_id_map, tmp);
}
-int __init io_apic_get_version (int ioapic)
+int __init io_apic_get_version(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
}
-int __init io_apic_get_redir_entries (int ioapic)
+int __init io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
}
-int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low)
+int io_apic_set_pci_routing(int ioapic, int pin, int irq, int edge_level, int active_high_low)
{
struct IO_APIC_route_entry entry;
* corresponding device driver registers for this IRQ.
*/
- memset(&entry,0,sizeof(entry));
+ memset(&entry, 0, sizeof(entry));
entry.delivery_mode = INT_DELIVERY_MODE;
entry.dest_mode = INT_DEST_MODE;
apic_printk(APIC_DEBUG, KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry "
"(%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i)\n", ioapic,
- mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq,
+ mp_ioapics[ioapic].mp_apicid, pin, entry.vector, irq,
edge_level, active_high_low);
ioapic_register_intr(irq, entry.vector, edge_level);
return -1;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_irqtype == mp_INT &&
- mp_irqs[i].mpc_srcbusirq == bus_irq)
+ if (mp_irqs[i].mp_irqtype == mp_INT &&
+ mp_irqs[i].mp_srcbusirq == bus_irq)
break;
if (i >= mp_irq_entries)
return -1;
return 0;
}
early_param("noapic", parse_noapic);
+
+void __init ioapic_init_mappings(void)
+{
+ unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
+ int i;
+
+ for (i = 0; i < nr_ioapics; i++) {
+ if (smp_found_config) {
+ ioapic_phys = mp_ioapics[i].mp_apicaddr;
+ if (!ioapic_phys) {
+ printk(KERN_ERR
+ "WARNING: bogus zero IO-APIC "
+ "address found in MPTABLE, "
+ "disabling IO/APIC support!\n");
+ smp_found_config = 0;
+ skip_ioapic_setup = 1;
+ goto fake_ioapic_page;
+ }
+ } else {
+fake_ioapic_page:
+ ioapic_phys = (unsigned long)
+ alloc_bootmem_pages(PAGE_SIZE);
+ ioapic_phys = __pa(ioapic_phys);
+ }
+ set_fixmap_nocache(idx, ioapic_phys);
+ printk(KERN_DEBUG "mapped IOAPIC to %08lx (%08lx)\n",
+ __fix_to_virt(idx), ioapic_phys);
+ idx++;
+ }
+}
+
};
/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
[0] = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, },
[1] = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, },
[2] = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, },
static int assign_irq_vector(int irq, cpumask_t mask);
+int first_system_vector = 0xfe;
+
+char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+
#define __apicdebuginit __init
int sis_apic_bug; /* not actually supported, dummy for compile */
static int disable_timer_pin_1 __initdata;
-int timer_over_8254 __initdata = 1;
+int timer_through_8259 __initdata;
/* Where if anywhere is the i8259 connect in external int mode */
static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
int nr_ioapic_registers[MAX_IO_APICS];
/* I/O APIC entries */
-struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS];
+struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
int nr_ioapics;
/* MP IRQ source entries */
-struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
/* # of MP IRQ source entries */
int mp_irq_entries;
+DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+
/*
* Rough estimation of how many shared IRQs there are, can
* be changed anytime.
static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
{
return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
- + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK);
+ + (mp_ioapics[idx].mp_apicaddr & ~PAGE_MASK);
}
static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
break;
reg = io_apic_read(entry->apic, 0x10 + pin*2);
/* Is the remote IRR bit set? */
- if ((reg >> 14) & 1) {
+ if (reg & IO_APIC_REDIR_REMOTE_IRR) {
spin_unlock_irqrestore(&ioapic_lock, flags);
return true;
}
break;
io_apic_write(apic, 0x11 + pin*2, dest);
reg = io_apic_read(apic, 0x10 + pin*2);
- reg &= ~0x000000ff;
+ reg &= ~IO_APIC_REDIR_VECTOR_MASK;
reg |= vector;
io_apic_modify(apic, reg);
if (!entry->next)
entry->pin = pin;
}
+/*
+ * Reroute an IRQ to a different pin.
+ */
+static void __init replace_pin_at_irq(unsigned int irq,
+ int oldapic, int oldpin,
+ int newapic, int newpin)
+{
+ struct irq_pin_list *entry = irq_2_pin + irq;
+
+ while (1) {
+ if (entry->apic == oldapic && entry->pin == oldpin) {
+ entry->apic = newapic;
+ entry->pin = newpin;
+ }
+ if (!entry->next)
+ break;
+ entry = irq_2_pin + entry->next;
+ }
+}
+
#define DO_ACTION(name,R,ACTION, FINAL) \
\
static void name##_IO_APIC_irq (unsigned int irq) \
__DO_ACTION(R, ACTION, FINAL)
-DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) )
- /* mask = 1 */
-DO_ACTION( __unmask, 0, &= 0xfffeffff, )
- /* mask = 0 */
+/* mask = 1 */
+DO_ACTION(__mask, 0, |= IO_APIC_REDIR_MASKED, io_apic_sync(entry->apic))
+
+/* mask = 0 */
+DO_ACTION(__unmask, 0, &= ~IO_APIC_REDIR_MASKED, )
static void mask_IO_APIC_irq (unsigned int irq)
{
}
__setup("disable_timer_pin_1", disable_timer_pin_setup);
-static int __init setup_disable_8254_timer(char *s)
-{
- timer_over_8254 = -1;
- return 1;
-}
-static int __init setup_enable_8254_timer(char *s)
-{
- timer_over_8254 = 2;
- return 1;
-}
-
-__setup("disable_8254_timer", setup_disable_8254_timer);
-__setup("enable_8254_timer", setup_enable_8254_timer);
-
/*
* Find the IRQ entry number of a certain pin.
int i;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_irqtype == type &&
- (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid ||
- mp_irqs[i].mpc_dstapic == MP_APIC_ALL) &&
- mp_irqs[i].mpc_dstirq == pin)
+ if (mp_irqs[i].mp_irqtype == type &&
+ (mp_irqs[i].mp_dstapic == mp_ioapics[apic].mp_apicid ||
+ mp_irqs[i].mp_dstapic == MP_APIC_ALL) &&
+ mp_irqs[i].mp_dstirq == pin)
return i;
return -1;
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mpc_irqtype == type) &&
- (mp_irqs[i].mpc_srcbusirq == irq))
+ (mp_irqs[i].mp_irqtype == type) &&
+ (mp_irqs[i].mp_srcbusirq == irq))
- return mp_irqs[i].mpc_dstirq;
+ return mp_irqs[i].mp_dstirq;
}
return -1;
}
int i;
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
if (test_bit(lbus, mp_bus_not_pci) &&
- (mp_irqs[i].mpc_irqtype == type) &&
- (mp_irqs[i].mpc_srcbusirq == irq))
+ (mp_irqs[i].mp_irqtype == type) &&
+ (mp_irqs[i].mp_srcbusirq == irq))
break;
}
if (i < mp_irq_entries) {
int apic;
for(apic = 0; apic < nr_ioapics; apic++) {
- if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
+ if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
return apic;
}
}
apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
bus, slot, pin);
- if (mp_bus_id_to_pci_bus[bus] == -1) {
+ if (test_bit(bus, mp_bus_not_pci)) {
apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
return -1;
}
for (i = 0; i < mp_irq_entries; i++) {
- int lbus = mp_irqs[i].mpc_srcbus;
+ int lbus = mp_irqs[i].mp_srcbus;
for (apic = 0; apic < nr_ioapics; apic++)
- if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic ||
- mp_irqs[i].mpc_dstapic == MP_APIC_ALL)
+ if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic ||
+ mp_irqs[i].mp_dstapic == MP_APIC_ALL)
break;
if (!test_bit(lbus, mp_bus_not_pci) &&
- !mp_irqs[i].mpc_irqtype &&
+ !mp_irqs[i].mp_irqtype &&
(bus == lbus) &&
- (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
- int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);
+ (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
+ int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
if (!(apic || IO_APIC_IRQ(irq)))
continue;
- if (pin == (mp_irqs[i].mpc_srcbusirq & 3))
+ if (pin == (mp_irqs[i].mp_srcbusirq & 3))
return irq;
/*
* Use the first all-but-pin matching entry as a
static int MPBIOS_polarity(int idx)
{
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
int polarity;
/*
* Determine IRQ line polarity (high active or low active):
*/
- switch (mp_irqs[idx].mpc_irqflag & 3)
+ switch (mp_irqs[idx].mp_irqflag & 3)
{
case 0: /* conforms, ie. bus-type dependent polarity */
if (test_bit(bus, mp_bus_not_pci))
static int MPBIOS_trigger(int idx)
{
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
int trigger;
/*
* Determine IRQ trigger mode (edge or level sensitive):
*/
- switch ((mp_irqs[idx].mpc_irqflag>>2) & 3)
+ switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
{
case 0: /* conforms, ie. bus-type dependent */
if (test_bit(bus, mp_bus_not_pci))
static int pin_2_irq(int idx, int apic, int pin)
{
int irq, i;
- int bus = mp_irqs[idx].mpc_srcbus;
+ int bus = mp_irqs[idx].mp_srcbus;
/*
* Debugging check, we are in big trouble if this message pops up!
*/
- if (mp_irqs[idx].mpc_dstirq != pin)
+ if (mp_irqs[idx].mp_dstirq != pin)
printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
if (test_bit(bus, mp_bus_not_pci)) {
- irq = mp_irqs[idx].mpc_srcbusirq;
+ irq = mp_irqs[idx].mp_srcbusirq;
} else {
/*
* PCI IRQs are mapped in order
offset = current_offset;
next:
vector += 8;
- if (vector >= FIRST_SYSTEM_VECTOR) {
+ if (vector >= first_system_vector) {
/* If we run out of vectors on large boxen, must share them. */
offset = (offset + 1) % 8;
vector = FIRST_DEVICE_VECTOR + offset;
cpus_clear(cfg->domain);
}
-void __setup_vector_irq(int cpu)
+static void __setup_vector_irq(int cpu)
{
/* Initialize vector_irq on a new cpu */
/* This function must be called with vector_lock held */
}
}
+void setup_vector_irq(int cpu)
+{
+ spin_lock(&vector_lock);
+ __setup_vector_irq(smp_processor_id());
+ spin_unlock(&vector_lock);
+}
+
static struct irq_chip ioapic_chip;
apic_printk(APIC_VERBOSE,KERN_DEBUG
"IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
"IRQ %d Mode:%i Active:%i)\n",
- apic, mp_ioapics[apic].mpc_apicid, pin, cfg->vector,
+ apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
irq, trigger, polarity);
/*
idx = find_irq_entry(apic,pin,mp_INT);
if (idx == -1) {
if (first_notcon) {
- apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mpc_apicid, pin);
+ apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mp_apicid, pin);
first_notcon = 0;
} else
- apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin);
+ apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mp_apicid, pin);
continue;
}
if (!first_notcon) {
}
/*
- * Set up the 8259A-master output pin as broadcast to all
- * CPUs.
+ * Set up the timer pin, possibly with the 8259A-master behind.
*/
-static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, int vector)
+static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
+ int vector)
{
struct IO_APIC_route_entry entry;
memset(&entry, 0, sizeof(entry));
- disable_8259A_irq(0);
-
- /* mask LVT0 */
- apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
-
/*
* We use logical delivery to get the timer IRQ
* to the first CPU.
*/
entry.dest_mode = INT_DEST_MODE;
- entry.mask = 0; /* unmask IRQ now */
+ entry.mask = 1; /* mask IRQ now */
entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
entry.delivery_mode = INT_DELIVERY_MODE;
entry.polarity = 0;
/*
* The timer IRQ doesn't have to know that behind the
- * scene we have a 8259A-master in AEOI mode ...
+ * scene we may have a 8259A-master in AEOI mode ...
*/
set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
* Add it to the IO-APIC irq-routing table:
*/
ioapic_write_entry(apic, pin, entry);
-
- enable_8259A_irq(0);
}
void __apicdebuginit print_IO_APIC(void)
printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
for (i = 0; i < nr_ioapics; i++)
printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n",
- mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]);
+ mp_ioapics[i].mp_apicid, nr_ioapic_registers[i]);
/*
* We are a bit conservative about what we expect. We have to
spin_unlock_irqrestore(&ioapic_lock, flags);
printk("\n");
- printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid);
+ printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID);
printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(read_apic_id()));
v = apic_read(APIC_LVR);
printk(KERN_INFO "... APIC VERSION: %08x\n", v);
void print_all_local_APICs (void)
{
- on_each_cpu(print_local_APIC, NULL, 1, 1);
+ on_each_cpu(print_local_APIC, NULL, 1);
}
void __apicdebuginit print_PIC(void)
}
}
-static void enable_lapic_irq (unsigned int irq)
+static void unmask_lapic_irq(unsigned int irq)
{
unsigned long v;
apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
}
-static void disable_lapic_irq (unsigned int irq)
+static void mask_lapic_irq(unsigned int irq)
{
unsigned long v;
ack_APIC_irq();
}
-static void end_lapic_irq (unsigned int i) { /* nothing */ }
-
-static struct hw_interrupt_type lapic_irq_type __read_mostly = {
- .name = "local-APIC",
- .typename = "local-APIC-edge",
- .startup = NULL, /* startup_irq() not used for IRQ0 */
- .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */
- .enable = enable_lapic_irq,
- .disable = disable_lapic_irq,
- .ack = ack_lapic_irq,
- .end = end_lapic_irq,
+static struct irq_chip lapic_chip __read_mostly = {
+ .name = "local-APIC",
+ .mask = mask_lapic_irq,
+ .unmask = unmask_lapic_irq,
+ .ack = ack_lapic_irq,
};
+static void lapic_register_intr(int irq)
+{
+ irq_desc[irq].status &= ~IRQ_LEVEL;
+ set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
+ "edge");
+}
+
static void __init setup_nmi(void)
{
/*
struct irq_cfg *cfg = irq_cfg + 0;
int apic1, pin1, apic2, pin2;
unsigned long flags;
+ int no_pin1 = 0;
local_irq_save(flags);
assign_irq_vector(0, TARGET_CPUS);
/*
- * Subtle, code in do_timer_interrupt() expects an AEOI
- * mode for the 8259A whenever interrupts are routed
- * through I/O APICs. Also IRQ0 has to be enabled in
- * the 8259A which implies the virtual wire has to be
- * disabled in the local APIC.
+ * As IRQ0 is to be enabled in the 8259A, the virtual
+ * wire has to be disabled in the local APIC.
*/
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
init_8259A(1);
- if (timer_over_8254 > 0)
- enable_8259A_irq(0);
pin1 = find_isa_irq_pin(0, mp_INT);
apic1 = find_isa_irq_apic(0, mp_INT);
apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
cfg->vector, apic1, pin1, apic2, pin2);
+ /*
+ * Some BIOS writers are clueless and report the ExtINTA
+ * I/O APIC input from the cascaded 8259A as the timer
+ * interrupt input. So just in case, if only one pin
+ * was found above, try it both directly and through the
+ * 8259A.
+ */
+ if (pin1 == -1) {
+ pin1 = pin2;
+ apic1 = apic2;
+ no_pin1 = 1;
+ } else if (pin2 == -1) {
+ pin2 = pin1;
+ apic2 = apic1;
+ }
+
if (pin1 != -1) {
/*
* Ok, does IRQ0 through the IOAPIC work?
*/
+ if (no_pin1) {
+ add_pin_to_irq(0, apic1, pin1);
+ setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
+ }
unmask_IO_APIC_irq(0);
if (!no_timer_check && timer_irq_works()) {
- nmi_watchdog_default();
if (nmi_watchdog == NMI_IO_APIC) {
- disable_8259A_irq(0);
setup_nmi();
enable_8259A_irq(0);
}
goto out;
}
clear_IO_APIC_pin(apic1, pin1);
- apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not "
- "connected to IO-APIC\n");
- }
+ if (!no_pin1)
+ apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: "
+ "8254 timer not connected to IO-APIC\n");
- apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) "
- "through the 8259A ... ");
- if (pin2 != -1) {
+ apic_printk(APIC_VERBOSE,KERN_INFO
+ "...trying to set up timer (IRQ0) "
+ "through the 8259A ... ");
apic_printk(APIC_VERBOSE,"\n..... (found apic %d pin %d) ...",
apic2, pin2);
/*
* legacy devices should be connected to IO APIC #0
*/
- setup_ExtINT_IRQ0_pin(apic2, pin2, cfg->vector);
+ replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+ setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
+ unmask_IO_APIC_irq(0);
+ enable_8259A_irq(0);
if (timer_irq_works()) {
apic_printk(APIC_VERBOSE," works.\n");
- nmi_watchdog_default();
+ timer_through_8259 = 1;
if (nmi_watchdog == NMI_IO_APIC) {
+ disable_8259A_irq(0);
setup_nmi();
+ enable_8259A_irq(0);
}
goto out;
}
/*
* Cleanup, just in case ...
*/
+ disable_8259A_irq(0);
clear_IO_APIC_pin(apic2, pin2);
+ apic_printk(APIC_VERBOSE," failed.\n");
}
- apic_printk(APIC_VERBOSE," failed.\n");
if (nmi_watchdog == NMI_IO_APIC) {
printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
- nmi_watchdog = 0;
+ nmi_watchdog = NMI_NONE;
}
apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
- disable_8259A_irq(0);
- irq_desc[0].chip = &lapic_irq_type;
+ lapic_register_intr(0);
apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */
enable_8259A_irq(0);
apic_printk(APIC_VERBOSE," works.\n");
goto out;
}
+ disable_8259A_irq(0);
apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
apic_printk(APIC_VERBOSE," failed.\n");
__setup("no_timer_check", notimercheck);
/*
- *
- * IRQs that are handled by the PIC in the MPS IOAPIC case.
- * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
- * Linux doesn't really care, as it's not actually used
- * for any interrupt handling anyway.
+ * Traditionally ISA IRQ2 is the cascade IRQ, and is not available
+ * to devices. However there may be an I/O APIC pin available for
+ * this interrupt regardless. The pin may be left unconnected, but
+ * typically it will be reused as an ExtINT cascade interrupt for
+ * the master 8259A. In the MPS case such a pin will normally be
+ * reported as an ExtINT interrupt in the MP table. With ACPI
+ * there is no provision for ExtINT interrupts, and in the absence
+ * of an override it would be treated as an ordinary ISA I/O APIC
+ * interrupt, that is edge-triggered and unmasked by default. We
+ * used to do this, but it caused problems on some systems because
+ * of the NMI watchdog and sometimes IRQ0 of the 8254 timer using
+ * the same ExtINT cascade interrupt to drive the local APIC of the
+ * bootstrap processor. Therefore we refrain from routing IRQ2 to
+ * the I/O APIC in all cases now. No actual device should request
+ * it anyway. --macro
*/
#define PIC_IRQS (1<<2)
* calling enable_IO_APIC() is moved to setup_local_APIC for BP
*/
- if (acpi_ioapic)
- io_apic_irqs = ~0; /* all IRQs go through IOAPIC */
- else
- io_apic_irqs = ~PIC_IRQS;
+ io_apic_irqs = ~PIC_IRQS;
apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
spin_lock_irqsave(&ioapic_lock, flags);
reg_00.raw = io_apic_read(dev->id, 0);
- if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) {
- reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid;
+ if (reg_00.bits.ID != mp_ioapics[dev->id].mp_apicid) {
+ reg_00.bits.ID = mp_ioapics[dev->id].mp_apicid;
io_apic_write(dev->id, 0, reg_00.raw);
}
spin_unlock_irqrestore(&ioapic_lock, flags);
return -1;
for (i = 0; i < mp_irq_entries; i++)
- if (mp_irqs[i].mpc_irqtype == mp_INT &&
- mp_irqs[i].mpc_srcbusirq == bus_irq)
+ if (mp_irqs[i].mp_irqtype == mp_INT &&
+ mp_irqs[i].mp_srcbusirq == bus_irq)
break;
if (i >= mp_irq_entries)
return -1;
ioapic_res = ioapic_setup_resources();
for (i = 0; i < nr_ioapics; i++) {
if (smp_found_config) {
- ioapic_phys = mp_ioapics[i].mpc_apicaddr;
+ ioapic_phys = mp_ioapics[i].mp_apicaddr;
} else {
ioapic_phys = (unsigned long)
alloc_bootmem_pages(PAGE_SIZE);
--- /dev/null
+#include <linux/linkage.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/kernel_stat.h>
+#include <linux/sysdev.h>
+#include <linux/bitops.h>
+
+#include <asm/acpi.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/hw_irq.h>
+#include <asm/pgtable.h>
+#include <asm/delay.h>
+#include <asm/desc.h>
+#include <asm/apic.h>
+#include <asm/i8259.h>
+
+/*
+ * Common place to define all x86 IRQ vectors
+ *
+ * This builds up the IRQ handler stubs using some ugly macros in irq.h
+ *
+ * These macros create the low-level assembly IRQ routines that save
+ * register context and call do_IRQ(). do_IRQ() then does all the
+ * operations that are needed to keep the AT (or SMP IOAPIC)
+ * interrupt-controller happy.
+ */
+
+#define IRQ_NAME2(nr) nr##_interrupt(void)
+#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
+
+/*
+ * SMP has a few special interrupts for IPI messages
+ */
+
+#define BUILD_IRQ(nr) \
+ asmlinkage void IRQ_NAME(nr); \
+ asm("\n.p2align\n" \
+ "IRQ" #nr "_interrupt:\n\t" \
+ "push $~(" #nr ") ; " \
+ "jmp common_interrupt");
+
+#define BI(x,y) \
+ BUILD_IRQ(x##y)
+
+#define BUILD_16_IRQS(x) \
+ BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
+ BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
+ BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
+ BI(x,c) BI(x,d) BI(x,e) BI(x,f)
+
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
+
+/*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
+ BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
+BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
+BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
+BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
+
+#undef BUILD_16_IRQS
+#undef BI
+
+
+#define IRQ(x,y) \
+ IRQ##x##y##_interrupt
+
+#define IRQLIST_16(x) \
+ IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
+ IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
+ IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
+ IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
+
+/* for the irq vectors */
+static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
+ IRQLIST_16(0x2), IRQLIST_16(0x3),
+ IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
+ IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
+ IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
+};
+
+#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,
+ [IRQ1_VECTOR] = 1,
+ [IRQ2_VECTOR] = 2,
+ [IRQ3_VECTOR] = 3,
+ [IRQ4_VECTOR] = 4,
+ [IRQ5_VECTOR] = 5,
+ [IRQ6_VECTOR] = 6,
+ [IRQ7_VECTOR] = 7,
+ [IRQ8_VECTOR] = 8,
+ [IRQ9_VECTOR] = 9,
+ [IRQ10_VECTOR] = 10,
+ [IRQ11_VECTOR] = 11,
+ [IRQ12_VECTOR] = 12,
+ [IRQ13_VECTOR] = 13,
+ [IRQ14_VECTOR] = 14,
+ [IRQ15_VECTOR] = 15,
+ [IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
+};
+
+static void __init init_ISA_irqs (void)
+{
+ int i;
+
+ init_bsp_APIC();
+ init_8259A(0);
+
+ for (i = 0; i < NR_IRQS; i++) {
+ irq_desc[i].status = IRQ_DISABLED;
+ irq_desc[i].action = NULL;
+ irq_desc[i].depth = 1;
+
+ if (i < 16) {
+ /*
+ * 16 old-style INTA-cycle interrupts:
+ */
+ set_irq_chip_and_handler_name(i, &i8259A_chip,
+ handle_level_irq, "XT");
+ } else {
+ /*
+ * 'high' PCI IRQs filled in on demand
+ */
+ irq_desc[i].chip = &no_irq_chip;
+ }
+ }
+}
+
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
+
+void __init native_init_IRQ(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
+ * IPI, driven by wakeup.
+ */
+ alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+
+ /* IPIs for invalidation */
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+ alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
+
+ /* IPI for generic function call */
+ alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+
++ /* IPI for generic single function call */
++ alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
++ call_function_single_interrupt);
++
+ /* Low priority IPI to cleanup after moving an irq */
+ set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
+#endif
+ alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+ alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+
+ /* self generated IPI for local APIC timer */
+ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+
+ /* IPI vectors for APIC spurious and error interrupts */
+ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+ alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+ if (!acpi_ioapic)
+ setup_irq(2, &irq2);
+}
#include <asm/mmu_context.h>
#ifdef CONFIG_SMP
-static void flush_ldt(void *null)
+static void flush_ldt(void *current_mm)
{
- if (current->active_mm)
+ if (current->active_mm == current_mm)
load_LDT(¤t->active_mm->context);
}
#endif
load_LDT(pc);
mask = cpumask_of_cpu(smp_processor_id());
if (!cpus_equal(current->mm->cpu_vm_mask, mask))
- smp_call_function(flush_ldt, current->mm, 1, 1);
- smp_call_function(flush_ldt, NULL, 1);
++ smp_call_function(flush_ldt, current->mm, 1);
preempt_enable();
#else
load_LDT(pc);
--- /dev/null
- smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0);
+/*
+ * NMI watchdog support on APIC systems
+ *
+ * Started by Ingo Molnar <mingo@redhat.com>
+ *
+ * Fixes:
+ * Mikael Pettersson : AMD K7 support for local APIC NMI watchdog.
+ * Mikael Pettersson : Power Management for local APIC NMI watchdog.
+ * Mikael Pettersson : Pentium 4 support for local APIC NMI watchdog.
+ * Pavel Machek and
+ * Mikael Pettersson : PM converted to driver model. Disable/enable API.
+ */
+
+#include <asm/apic.h>
+
+#include <linux/nmi.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/sysdev.h>
+#include <linux/sysctl.h>
+#include <linux/percpu.h>
+#include <linux/kprobes.h>
+#include <linux/cpumask.h>
+#include <linux/kernel_stat.h>
+#include <linux/kdebug.h>
+#include <linux/smp.h>
+
+#include <asm/i8259.h>
+#include <asm/io_apic.h>
+#include <asm/smp.h>
+#include <asm/nmi.h>
+#include <asm/proto.h>
+#include <asm/timer.h>
+
+#include <asm/mce.h>
+
+#include <mach_traps.h>
+
+int unknown_nmi_panic;
+int nmi_watchdog_enabled;
+
+static cpumask_t backtrace_mask = CPU_MASK_NONE;
+
+/* nmi_active:
+ * >0: the lapic NMI watchdog is active, but can be disabled
+ * <0: the lapic NMI watchdog has not been set up, and cannot
+ * be enabled
+ * 0: the lapic NMI watchdog is disabled, but can be enabled
+ */
+atomic_t nmi_active = ATOMIC_INIT(0); /* oprofile uses this */
+EXPORT_SYMBOL(nmi_active);
+
+unsigned int nmi_watchdog = NMI_NONE;
+EXPORT_SYMBOL(nmi_watchdog);
+
+static int panic_on_timeout;
+
+static unsigned int nmi_hz = HZ;
+static DEFINE_PER_CPU(short, wd_enabled);
+static int endflag __initdata;
+
+static inline unsigned int get_nmi_count(int cpu)
+{
+#ifdef CONFIG_X86_64
+ return cpu_pda(cpu)->__nmi_count;
+#else
+ return nmi_count(cpu);
+#endif
+}
+
+static inline int mce_in_progress(void)
+{
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
+ return atomic_read(&mce_entry) > 0;
+#endif
+ return 0;
+}
+
+/*
+ * Take the local apic timer and PIT/HPET into account. We don't
+ * know which one is active, when we have highres/dyntick on
+ */
+static inline unsigned int get_timer_irqs(int cpu)
+{
+#ifdef CONFIG_X86_64
+ return read_pda(apic_timer_irqs) + read_pda(irq0_irqs);
+#else
+ return per_cpu(irq_stat, cpu).apic_timer_irqs +
+ per_cpu(irq_stat, cpu).irq0_irqs;
+#endif
+}
+
+#ifdef CONFIG_SMP
+/*
+ * The performance counters used by NMI_LOCAL_APIC don't trigger when
+ * the CPU is idle. To make sure the NMI watchdog really ticks on all
+ * CPUs during the test make them busy.
+ */
+static __init void nmi_cpu_busy(void *data)
+{
+ local_irq_enable_in_hardirq();
+ /*
+ * Intentionally don't use cpu_relax here. This is
+ * to make sure that the performance counter really ticks,
+ * even if there is a simulator or similar that catches the
+ * pause instruction. On a real HT machine this is fine because
+ * all other CPUs are busy with "useless" delay loops and don't
+ * care if they get somewhat less cycles.
+ */
+ while (endflag == 0)
+ mb();
+}
+#endif
+
+int __init check_nmi_watchdog(void)
+{
+ unsigned int *prev_nmi_count;
+ int cpu;
+
+ if (!nmi_watchdog_active() || !atomic_read(&nmi_active))
+ return 0;
+
+ prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
+ if (!prev_nmi_count)
+ goto error;
+
+ printk(KERN_INFO "Testing NMI watchdog ... ");
+
+#ifdef CONFIG_SMP
+ if (nmi_watchdog == NMI_LOCAL_APIC)
- on_each_cpu(__acpi_nmi_enable, NULL, 0, 1);
++ smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
+#endif
+
+ for_each_possible_cpu(cpu)
+ prev_nmi_count[cpu] = get_nmi_count(cpu);
+ local_irq_enable();
+ mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
+
+ for_each_online_cpu(cpu) {
+ if (!per_cpu(wd_enabled, cpu))
+ continue;
+ if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) {
+ printk(KERN_WARNING "WARNING: CPU#%d: NMI "
+ "appears to be stuck (%d->%d)!\n",
+ cpu,
+ prev_nmi_count[cpu],
+ get_nmi_count(cpu));
+ per_cpu(wd_enabled, cpu) = 0;
+ atomic_dec(&nmi_active);
+ }
+ }
+ endflag = 1;
+ if (!atomic_read(&nmi_active)) {
+ kfree(prev_nmi_count);
+ atomic_set(&nmi_active, -1);
+ goto error;
+ }
+ printk("OK.\n");
+
+ /*
+ * now that we know it works we can reduce NMI frequency to
+ * something more reasonable; makes a difference in some configs
+ */
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ nmi_hz = lapic_adjust_nmi_hz(1);
+
+ kfree(prev_nmi_count);
+ return 0;
+error:
+ if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
+ disable_8259A_irq(0);
+#ifdef CONFIG_X86_32
+ timer_ack = 0;
+#endif
+ return -1;
+}
+
+static int __init setup_nmi_watchdog(char *str)
+{
+ unsigned int nmi;
+
+ if (!strncmp(str, "panic", 5)) {
+ panic_on_timeout = 1;
+ str = strchr(str, ',');
+ if (!str)
+ return 1;
+ ++str;
+ }
+
+ get_option(&str, &nmi);
+
+ if (nmi >= NMI_INVALID)
+ return 0;
+
+ nmi_watchdog = nmi;
+ return 1;
+}
+__setup("nmi_watchdog=", setup_nmi_watchdog);
+
+/*
+ * Suspend/resume support
+ */
+#ifdef CONFIG_PM
+
+static int nmi_pm_active; /* nmi_active before suspend */
+
+static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
+{
+ /* only CPU0 goes here, other CPUs should be offline */
+ nmi_pm_active = atomic_read(&nmi_active);
+ stop_apic_nmi_watchdog(NULL);
+ BUG_ON(atomic_read(&nmi_active) != 0);
+ return 0;
+}
+
+static int lapic_nmi_resume(struct sys_device *dev)
+{
+ /* only CPU0 goes here, other CPUs should be offline */
+ if (nmi_pm_active > 0) {
+ setup_apic_nmi_watchdog(NULL);
+ touch_nmi_watchdog();
+ }
+ return 0;
+}
+
+static struct sysdev_class nmi_sysclass = {
+ .name = "lapic_nmi",
+ .resume = lapic_nmi_resume,
+ .suspend = lapic_nmi_suspend,
+};
+
+static struct sys_device device_lapic_nmi = {
+ .id = 0,
+ .cls = &nmi_sysclass,
+};
+
+static int __init init_lapic_nmi_sysfs(void)
+{
+ int error;
+
+ /*
+ * should really be a BUG_ON but b/c this is an
+ * init call, it just doesn't work. -dcz
+ */
+ if (nmi_watchdog != NMI_LOCAL_APIC)
+ return 0;
+
+ if (atomic_read(&nmi_active) < 0)
+ return 0;
+
+ error = sysdev_class_register(&nmi_sysclass);
+ if (!error)
+ error = sysdev_register(&device_lapic_nmi);
+ return error;
+}
+
+/* must come after the local APIC's device_initcall() */
+late_initcall(init_lapic_nmi_sysfs);
+
+#endif /* CONFIG_PM */
+
+static void __acpi_nmi_enable(void *__unused)
+{
+ apic_write_around(APIC_LVT0, APIC_DM_NMI);
+}
+
+/*
+ * Enable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_enable(void)
+{
+ if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
- on_each_cpu(__acpi_nmi_disable, NULL, 0, 1);
++ on_each_cpu(__acpi_nmi_enable, NULL, 1);
+}
+
+static void __acpi_nmi_disable(void *__unused)
+{
+ apic_write_around(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
+}
+
+/*
+ * Disable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_disable(void)
+{
+ if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
++ on_each_cpu(__acpi_nmi_disable, NULL, 1);
+}
+
+void setup_apic_nmi_watchdog(void *unused)
+{
+ if (__get_cpu_var(wd_enabled))
+ return;
+
+ /* cheap hack to support suspend/resume */
+ /* if cpu0 is not active neither should the other cpus */
+ if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0)
+ return;
+
+ switch (nmi_watchdog) {
+ case NMI_LOCAL_APIC:
+ /* enable it before to avoid race with handler */
+ __get_cpu_var(wd_enabled) = 1;
+ if (lapic_watchdog_init(nmi_hz) < 0) {
+ __get_cpu_var(wd_enabled) = 0;
+ return;
+ }
+ /* FALL THROUGH */
+ case NMI_IO_APIC:
+ __get_cpu_var(wd_enabled) = 1;
+ atomic_inc(&nmi_active);
+ }
+}
+
+void stop_apic_nmi_watchdog(void *unused)
+{
+ /* only support LOCAL and IO APICs for now */
+ if (!nmi_watchdog_active())
+ return;
+ if (__get_cpu_var(wd_enabled) == 0)
+ return;
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ lapic_watchdog_stop();
+ __get_cpu_var(wd_enabled) = 0;
+ atomic_dec(&nmi_active);
+}
+
+/*
+ * the best way to detect whether a CPU has a 'hard lockup' problem
+ * is to check it's local APIC timer IRQ counts. If they are not
+ * changing then that CPU has some problem.
+ *
+ * as these watchdog NMI IRQs are generated on every CPU, we only
+ * have to check the current processor.
+ *
+ * since NMIs don't listen to _any_ locks, we have to be extremely
+ * careful not to rely on unsafe variables. The printk might lock
+ * up though, so we have to break up any console locks first ...
+ * [when there will be more tty-related locks, break them up here too!]
+ */
+
+static DEFINE_PER_CPU(unsigned, last_irq_sum);
+static DEFINE_PER_CPU(local_t, alert_counter);
+static DEFINE_PER_CPU(int, nmi_touch);
+
+void touch_nmi_watchdog(void)
+{
+ if (nmi_watchdog_active()) {
+ unsigned cpu;
+
+ /*
+ * Tell other CPUs to reset their alert counters. We cannot
+ * do it ourselves because the alert count increase is not
+ * atomic.
+ */
+ for_each_present_cpu(cpu) {
+ if (per_cpu(nmi_touch, cpu) != 1)
+ per_cpu(nmi_touch, cpu) = 1;
+ }
+ }
+
+ /*
+ * Tickle the softlockup detector too:
+ */
+ touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL(touch_nmi_watchdog);
+
+notrace __kprobes int
+nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
+{
+ /*
+ * Since current_thread_info()-> is always on the stack, and we
+ * always switch the stack NMI-atomically, it's safe to use
+ * smp_processor_id().
+ */
+ unsigned int sum;
+ int touched = 0;
+ int cpu = smp_processor_id();
+ int rc = 0;
+
+ /* check for other users first */
+ if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
+ == NOTIFY_STOP) {
+ rc = 1;
+ touched = 1;
+ }
+
+ sum = get_timer_irqs(cpu);
+
+ if (__get_cpu_var(nmi_touch)) {
+ __get_cpu_var(nmi_touch) = 0;
+ touched = 1;
+ }
+
+ if (cpu_isset(cpu, backtrace_mask)) {
+ static DEFINE_SPINLOCK(lock); /* Serialise the printks */
+
+ spin_lock(&lock);
+ printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
+ dump_stack();
+ spin_unlock(&lock);
+ cpu_clear(cpu, backtrace_mask);
+ }
+
+ /* Could check oops_in_progress here too, but it's safer not to */
+ if (mce_in_progress())
+ touched = 1;
+
+ /* if the none of the timers isn't firing, this cpu isn't doing much */
+ if (!touched && __get_cpu_var(last_irq_sum) == sum) {
+ /*
+ * Ayiee, looks like this CPU is stuck ...
+ * wait a few IRQs (5 seconds) before doing the oops ...
+ */
+ local_inc(&__get_cpu_var(alert_counter));
+ if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz)
+ /*
+ * die_nmi will return ONLY if NOTIFY_STOP happens..
+ */
+ die_nmi("BUG: NMI Watchdog detected LOCKUP",
+ regs, panic_on_timeout);
+ } else {
+ __get_cpu_var(last_irq_sum) = sum;
+ local_set(&__get_cpu_var(alert_counter), 0);
+ }
+
+ /* see if the nmi watchdog went off */
+ if (!__get_cpu_var(wd_enabled))
+ return rc;
+ switch (nmi_watchdog) {
+ case NMI_LOCAL_APIC:
+ rc |= lapic_wd_event(nmi_hz);
+ break;
+ case NMI_IO_APIC:
+ /*
+ * don't know how to accurately check for this.
+ * just assume it was a watchdog timer interrupt
+ * This matches the old behaviour.
+ */
+ rc = 1;
+ break;
+ }
+ return rc;
+}
+
+#ifdef CONFIG_SYSCTL
+
+static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
+{
+ unsigned char reason = get_nmi_reason();
+ char buf[64];
+
+ sprintf(buf, "NMI received for unknown reason %02x\n", reason);
+ die_nmi(buf, regs, 1); /* Always panic here */
+ return 0;
+}
+
+/*
+ * proc handler for /proc/sys/kernel/nmi
+ */
+int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
+ void __user *buffer, size_t *length, loff_t *ppos)
+{
+ int old_state;
+
+ nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
+ old_state = nmi_watchdog_enabled;
+ proc_dointvec(table, write, file, buffer, length, ppos);
+ if (!!old_state == !!nmi_watchdog_enabled)
+ return 0;
+
+ if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) {
+ printk(KERN_WARNING
+ "NMI watchdog is permanently disabled\n");
+ return -EIO;
+ }
+
+ if (nmi_watchdog == NMI_LOCAL_APIC) {
+ if (nmi_watchdog_enabled)
+ enable_lapic_nmi_watchdog();
+ else
+ disable_lapic_nmi_watchdog();
+ } else {
+ printk(KERN_WARNING
+ "NMI watchdog doesn't know what hardware to touch\n");
+ return -EIO;
+ }
+ return 0;
+}
+
+#endif /* CONFIG_SYSCTL */
+
+int do_nmi_callback(struct pt_regs *regs, int cpu)
+{
+#ifdef CONFIG_SYSCTL
+ if (unknown_nmi_panic)
+ return unknown_nmi_panic_callback(regs, cpu);
+#endif
+ return 0;
+}
+
+void __trigger_all_cpu_backtrace(void)
+{
+ int i;
+
+ backtrace_mask = cpu_online_map;
+ /* Wait for up to 10 seconds for all CPUs to do the backtrace */
+ for (i = 0; i < 10 * 1000; i++) {
+ if (cpus_empty(backtrace_mask))
+ break;
+ mdelay(1);
+ }
+}
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/pm.h>
+#include <linux/clockchips.h>
struct kmem_cache *task_xstate_cachep;
SLAB_PANIC, NULL);
}
+/*
+ * Idle related variables and functions
+ */
+unsigned long boot_option_idle_override = 0;
+EXPORT_SYMBOL(boot_option_idle_override);
+
+/*
+ * Powermanagement idle function, if any..
+ */
+void (*pm_idle)(void);
+EXPORT_SYMBOL(pm_idle);
+
+#ifdef CONFIG_X86_32
+/*
+ * This halt magic was a workaround for ancient floppy DMA
+ * wreckage. It should be safe to remove.
+ */
+static int hlt_counter;
+void disable_hlt(void)
+{
+ hlt_counter++;
+}
+EXPORT_SYMBOL(disable_hlt);
+
+void enable_hlt(void)
+{
+ hlt_counter--;
+}
+EXPORT_SYMBOL(enable_hlt);
+
+static inline int hlt_use_halt(void)
+{
+ return (!hlt_counter && boot_cpu_data.hlt_works_ok);
+}
+#else
+static inline int hlt_use_halt(void)
+{
+ return 1;
+}
+#endif
+
+/*
+ * We use this if we don't have any better
+ * idle routine..
+ */
+void default_idle(void)
+{
+ if (hlt_use_halt()) {
+ current_thread_info()->status &= ~TS_POLLING;
+ /*
+ * TS_POLLING-cleared state must be visible before we
+ * test NEED_RESCHED:
+ */
+ smp_mb();
+
+ if (!need_resched())
+ safe_halt(); /* enables interrupts racelessly */
+ else
+ local_irq_enable();
+ current_thread_info()->status |= TS_POLLING;
+ } else {
+ local_irq_enable();
+ /* loop is done by the caller */
+ cpu_relax();
+ }
+}
+#ifdef CONFIG_APM_MODULE
+EXPORT_SYMBOL(default_idle);
+#endif
+
static void do_nothing(void *unused)
{
}
{
smp_mb();
/* kick all the CPUs so that they exit out of pm_idle */
- smp_call_function(do_nothing, NULL, 0, 1);
+ smp_call_function(do_nothing, NULL, 1);
}
EXPORT_SYMBOL_GPL(cpu_idle_wait);
*
* idle=mwait overrides this decision and forces the usage of mwait.
*/
+
+#define MWAIT_INFO 0x05
+#define MWAIT_ECX_EXTENDED_INFO 0x01
+#define MWAIT_EDX_C1 0xf0
+
static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
{
+ u32 eax, ebx, ecx, edx;
+
if (force_mwait)
return 1;
- if (c->x86_vendor == X86_VENDOR_AMD) {
- switch(c->x86) {
- case 0x10:
- case 0x11:
- return 0;
- }
- }
+ if (c->cpuid_level < MWAIT_INFO)
+ return 0;
+
+ cpuid(MWAIT_INFO, &eax, &ebx, &ecx, &edx);
+ /* Check, whether EDX has extended info about MWAIT */
+ if (!(ecx & MWAIT_ECX_EXTENDED_INFO))
+ return 1;
+
+ /*
+ * edx enumeratios MONITOR/MWAIT extensions. Check, whether
+ * C1 supports MWAIT
+ */
+ return (edx & MWAIT_EDX_C1);
+}
+
+/*
+ * Check for AMD CPUs, which have potentially C1E support
+ */
+static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
+{
+ if (c->x86_vendor != X86_VENDOR_AMD)
+ return 0;
+
+ if (c->x86 < 0x0F)
+ return 0;
+
+ /* Family 0x0f models < rev F do not have C1E */
+ if (c->x86 == 0x0f && c->x86_model < 0x40)
+ return 0;
+
return 1;
}
-void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
+/*
+ * C1E aware idle routine. We check for C1E active in the interrupt
+ * pending message MSR. If we detect C1E, then we handle it the same
+ * way as C3 power states (local apic timer and TSC stop)
+ */
+static void c1e_idle(void)
{
- static int selected;
+ static cpumask_t c1e_mask = CPU_MASK_NONE;
+ static int c1e_detected;
- if (selected)
+ if (need_resched())
return;
+
+ if (!c1e_detected) {
+ u32 lo, hi;
+
+ rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+ if (lo & K8_INTP_C1E_ACTIVE_MASK) {
+ c1e_detected = 1;
+ mark_tsc_unstable("TSC halt in C1E");
+ printk(KERN_INFO "System has C1E enabled\n");
+ }
+ }
+
+ if (c1e_detected) {
+ int cpu = smp_processor_id();
+
+ if (!cpu_isset(cpu, c1e_mask)) {
+ cpu_set(cpu, c1e_mask);
+ /*
+ * Force broadcast so ACPI can not interfere. Needs
+ * to run with interrupts enabled as it uses
+ * smp_function_call.
+ */
+ local_irq_enable();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
+ &cpu);
+ printk(KERN_INFO "Switch to broadcast mode on CPU%d\n",
+ cpu);
+ local_irq_disable();
+ }
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+
+ default_idle();
+
+ /*
+ * The switch back from broadcast mode needs to be
+ * called with interrupts disabled.
+ */
+ local_irq_disable();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+ local_irq_enable();
+ } else
+ default_idle();
+}
+
+void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
+{
#ifdef CONFIG_X86_SMP
if (pm_idle == poll_idle && smp_num_siblings > 1) {
printk(KERN_WARNING "WARNING: polling idle and HT enabled,"
" performance may degrade.\n");
}
#endif
+ if (pm_idle)
+ return;
+
if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
/*
- * Skip, if setup has overridden idle.
* One CPU supports mwait => All CPUs supports mwait
*/
- if (!pm_idle) {
- printk(KERN_INFO "using mwait in idle threads.\n");
- pm_idle = mwait_idle;
- }
- }
- selected = 1;
+ printk(KERN_INFO "using mwait in idle threads.\n");
+ pm_idle = mwait_idle;
+ } else if (check_c1e_idle(c)) {
+ printk(KERN_INFO "using C1E aware idle routine\n");
+ pm_idle = c1e_idle;
+ } else
+ pm_idle = default_idle;
}
static int __init idle_setup(char *str)
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mtrr.h>
-#include <asm/nmi.h>
#include <asm/vmi.h>
#include <asm/genapic.h>
#include <linux/mc146818rtc.h>
#include <mach_wakecpu.h>
#include <smpboot_hooks.h>
-/*
- * FIXME: For x86_64, those are defined in other files. But moving them here,
- * would make the setup areas dependent on smp, which is a loss. When we
- * integrate apic between arches, we can probably do a better job, but
- * right now, they'll stay here -- glommer
- */
-
-/* which logical CPU number maps to which CPU (physical APIC ID) */
-u16 x86_cpu_to_apicid_init[NR_CPUS] __initdata =
- { [0 ... NR_CPUS-1] = BAD_APICID };
-void *x86_cpu_to_apicid_early_ptr;
-
-u16 x86_bios_cpu_apicid_init[NR_CPUS] __initdata
- = { [0 ... NR_CPUS-1] = BAD_APICID };
-void *x86_bios_cpu_apicid_early_ptr;
-
#ifdef CONFIG_X86_32
u8 apicid_2_node[MAX_APICID];
static int low_mappings;
map_cpu_to_node(cpu, node);
}
-static void unmap_cpu_to_logical_apicid(int cpu)
+void numa_remove_cpu(int cpu)
{
cpu_2_logical_apicid[cpu] = BAD_APICID;
unmap_cpu_to_node(cpu);
}
#else
-#define unmap_cpu_to_logical_apicid(cpu) do {} while (0)
#define map_cpu_to_logical_apicid() do {} while (0)
#endif
* lock helps us to not include this cpu in a currently in progress
* smp_call_function().
*/
- lock_ipi_call_lock();
+ ipi_call_lock_irq();
-#ifdef CONFIG_X86_64
- spin_lock(&vector_lock);
-
- /* Setup the per cpu irq handling data structures */
- __setup_vector_irq(smp_processor_id());
- /*
- * Allow the master to continue.
- */
- spin_unlock(&vector_lock);
+#ifdef CONFIG_X86_IO_APIC
+ setup_vector_irq(smp_processor_id());
#endif
cpu_set(smp_processor_id(), cpu_online_map);
- unlock_ipi_call_lock();
+ ipi_call_unlock_irq();
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
setup_secondary_clock();
cpu_idle();
}
-#ifdef CONFIG_X86_32
-/*
- * Everything has been set up for the secondary
- * CPUs - they just need to reload everything
- * from the task structure
- * This function must not return.
- */
-void __devinit initialize_secondary(void)
-{
- /*
- * We don't actually need to load the full TSS,
- * basically just the stack pointer and the ip.
- */
-
- asm volatile(
- "movl %0,%%esp\n\t"
- "jmp *%1"
- :
- :"m" (current->thread.sp), "m" (current->thread.ip));
-}
-#endif
-
static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_32
/*
* Mask B, Pentium, but not Pentium MMX
*/
valid_k7:
;
-#endif
}
static void __cpuinit smp_checks(void)
return c->llc_shared_map;
}
-#ifdef CONFIG_X86_32
-/*
- * We are called very early to get the low memory for the
- * SMP bootup trampoline page.
- */
-void __init smp_alloc_memory(void)
-{
- trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE);
- /*
- * Has to be in very low memory so we can execute
- * real-mode AP code.
- */
- if (__pa(trampoline_base) >= 0x9F000)
- BUG();
-}
-#endif
-
static void impress_friends(void)
{
int cpu;
* target processor state.
*/
startup_ipi_hook(phys_apicid, (unsigned long) start_secondary,
-#ifdef CONFIG_X86_64
- (unsigned long)init_rsp);
-#else
(unsigned long)stack_start.sp);
-#endif
/*
* Run STARTUP IPI loop.
complete(&c_idle->done);
}
+#ifdef CONFIG_X86_64
+/*
+ * Allocate node local memory for the AP pda.
+ *
+ * Must be called after the _cpu_pda pointer table is initialized.
+ */
+static int __cpuinit get_local_pda(int cpu)
+{
+ struct x8664_pda *oldpda, *newpda;
+ unsigned long size = sizeof(struct x8664_pda);
+ int node = cpu_to_node(cpu);
+
+ if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem)
+ return 0;
+
+ oldpda = cpu_pda(cpu);
+ newpda = kmalloc_node(size, GFP_ATOMIC, node);
+ if (!newpda) {
+ printk(KERN_ERR "Could not allocate node local PDA "
+ "for CPU %d on node %d\n", cpu, node);
+
+ if (oldpda)
+ return 0; /* have a usable pda */
+ else
+ return -1;
+ }
+
+ if (oldpda) {
+ memcpy(newpda, oldpda, size);
+ if (!after_bootmem)
+ free_bootmem((unsigned long)oldpda, size);
+ }
+
+ newpda->in_bootmem = 0;
+ cpu_pda(cpu) = newpda;
+ return 0;
+}
+#endif /* CONFIG_X86_64 */
+
static int __cpuinit do_boot_cpu(int apicid, int cpu)
/*
* NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
};
INIT_WORK(&c_idle.work, do_fork_idle);
-#ifdef CONFIG_X86_64
- /* allocate memory for gdts of secondary cpus. Hotplug is considered */
- if (!cpu_gdt_descr[cpu].address &&
- !(cpu_gdt_descr[cpu].address = get_zeroed_page(GFP_KERNEL))) {
- printk(KERN_ERR "Failed to allocate GDT for CPU %d\n", cpu);
- return -1;
- }
+#ifdef CONFIG_X86_64
/* Allocate node local memory for AP pdas */
- if (cpu_pda(cpu) == &boot_cpu_pda[cpu]) {
- struct x8664_pda *newpda, *pda;
- int node = cpu_to_node(cpu);
- pda = cpu_pda(cpu);
- newpda = kmalloc_node(sizeof(struct x8664_pda), GFP_ATOMIC,
- node);
- if (newpda) {
- memcpy(newpda, pda, sizeof(struct x8664_pda));
- cpu_pda(cpu) = newpda;
- } else
- printk(KERN_ERR
- "Could not allocate node local PDA for CPU %d on node %d\n",
- cpu, node);
+ if (cpu > 0) {
+ boot_error = get_local_pda(cpu);
+ if (boot_error)
+ goto restore_state;
+ /* if can't get pda memory, can't start cpu */
}
#endif
#ifdef CONFIG_X86_32
per_cpu(current_task, cpu) = c_idle.idle;
init_gdt(cpu);
- early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
- c_idle.idle->thread.ip = (unsigned long) start_secondary;
/* Stack for startup_32 can be just as for start_secondary onwards */
- stack_start.sp = (void *) c_idle.idle->thread.sp;
irq_ctx_init(cpu);
#else
cpu_pda(cpu)->pcurrent = c_idle.idle;
- init_rsp = c_idle.idle->thread.sp;
- load_sp0(&per_cpu(init_tss, cpu), &c_idle.idle->thread);
- initial_code = (unsigned long)start_secondary;
clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
#endif
+ early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
+ initial_code = (unsigned long)start_secondary;
+ stack_start.sp = (void *) c_idle.idle->thread.sp;
/* start_ip had better be page-aligned! */
start_ip = setup_trampoline();
inquire_remote_apic(apicid);
}
}
-
- if (boot_error) {
- /* Try to put things back the way they were before ... */
- unmap_cpu_to_logical_apicid(cpu);
#ifdef CONFIG_X86_64
- clear_node_cpumask(cpu); /* was set by numa_add_cpu */
+restore_state:
#endif
+ if (boot_error) {
+ /* Try to put things back the way they were before ... */
+ numa_remove_cpu(cpu); /* was set by numa_add_cpu */
cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
- cpu_clear(cpu, cpu_possible_map);
cpu_clear(cpu, cpu_present_map);
per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
}
{
cpu_present_map = cpumask_of_cpu(0);
cpu_possible_map = cpumask_of_cpu(0);
-#ifdef CONFIG_X86_32
smpboot_clear_io_apic_irqs();
-#endif
+
if (smp_found_config)
- phys_cpu_present_map =
- physid_mask_of_physid(boot_cpu_physical_apicid);
+ physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
else
- phys_cpu_present_map = physid_mask_of_physid(0);
+ physid_set_mask_of_physid(0, &phys_cpu_present_map);
map_cpu_to_logical_apicid();
cpu_set(0, per_cpu(cpu_sibling_map, 0));
cpu_set(0, per_cpu(cpu_core_map, 0));
* If SMP should be disabled, then really disable it!
*/
if (!max_cpus) {
- printk(KERN_INFO "SMP mode deactivated,"
- "forcing use of dummy APIC emulation.\n");
+ printk(KERN_INFO "SMP mode deactivated.\n");
smpboot_clear_io_apic();
-#ifdef CONFIG_X86_32
+
+ localise_nmi_watchdog();
+
connect_bsp_APIC();
-#endif
setup_local_APIC();
end_local_APIC_setup();
return -1;
void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
preempt_disable();
- nmi_watchdog_default();
smp_cpu_index_default();
current_cpu_data = boot_cpu_data;
cpu_callin_map = cpumask_of_cpu(0);
}
preempt_enable();
-#ifdef CONFIG_X86_32
connect_bsp_APIC();
-#endif
+
/*
* Switch from PIC to APIC mode.
*/
int me = smp_processor_id();
#ifdef CONFIG_X86_32
init_gdt(me);
- switch_to_new_gdt();
#endif
+ switch_to_new_gdt();
/* already set me in cpu_online_map in boot_cpu_init() */
cpu_set(me, cpu_callout_map);
per_cpu(cpu_state, me) = CPU_ONLINE;
#ifdef CONFIG_HOTPLUG_CPU
-# ifdef CONFIG_X86_32
-void cpu_exit_clear(void)
-{
- int cpu = raw_smp_processor_id();
-
- idle_task_exit();
-
- cpu_uninit();
- irq_ctx_exit(cpu);
-
- cpu_clear(cpu, cpu_callout_map);
- cpu_clear(cpu, cpu_callin_map);
-
- unmap_cpu_to_logical_apicid(cpu);
-}
-# endif /* CONFIG_X86_32 */
-
static void remove_siblinginfo(int cpu)
{
int sibling;
int i;
int possible;
+ /* no processor from mptable or madt */
+ if (!num_processors)
+ num_processors = 1;
+
+#ifdef CONFIG_HOTPLUG_CPU
if (additional_cpus == -1) {
if (disabled_cpus > 0)
additional_cpus = disabled_cpus;
else
additional_cpus = 0;
}
+#else
+ additional_cpus = 0;
+#endif
possible = num_processors + additional_cpus;
if (possible > NR_CPUS)
possible = NR_CPUS;
for (i = 0; i < possible; i++)
cpu_set(i, cpu_possible_map);
+
+ nr_cpu_ids = possible;
}
static void __ref remove_cpu_from_maps(int cpu)
{
cpu_clear(cpu, cpu_online_map);
-#ifdef CONFIG_X86_64
cpu_clear(cpu, cpu_callout_map);
cpu_clear(cpu, cpu_callin_map);
/* was set by cpu_init() */
clear_bit(cpu, (unsigned long *)&cpu_initialized);
- clear_node_cpumask(cpu);
-#endif
+ numa_remove_cpu(cpu);
}
int __cpu_disable(void)
#include <asm/proto.h>
#include <asm/apicdef.h>
#include <asm/idle.h>
+#include <asm/uv/uv_hub.h>
+#include <asm/uv/uv_bau.h>
#include <mach_ipi.h>
/*
union smp_flush_state *f;
cpumask_t cpumask = *cpumaskp;
+ if (is_uv_system() && uv_flush_tlb_others(&cpumask, mm, va))
+ return;
+
/* Caller has disabled preemption */
sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
f = &per_cpu(flush_state, sender);
void flush_tlb_all(void)
{
- on_each_cpu(do_flush_tlb_all, NULL, 1, 1);
+ on_each_cpu(do_flush_tlb_all, NULL, 1);
}
#include <asm/topology.h>
#include <asm/vgtod.h>
-#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
+#define __vsyscall(nr) \
+ __attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace
#define __syscall_clobber "r11","cx","memory"
/*
doesn't violate that. We'll find out if it does. */
static void __cpuinit vsyscall_set_cpu(int cpu)
{
- unsigned long *d;
+ unsigned long d;
unsigned long node = 0;
#ifdef CONFIG_NUMA
node = cpu_to_node(cpu);
/* Store cpu number in limit so that it can be loaded quickly
in user space in vgetcpu.
12 bits for the CPU and 8 bits for the node. */
- d = (unsigned long *)(get_cpu_gdt_table(cpu) + GDT_ENTRY_PER_CPU);
- *d = 0x0f40000000000ULL;
- *d |= cpu;
- *d |= (node & 0xf) << 12;
- *d |= (node >> 4) << 48;
+ d = 0x0f40000000000ULL;
+ d |= cpu;
+ d |= (node & 0xf) << 12;
+ d |= (node >> 4) << 48;
+ write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
}
static void __cpuinit cpu_vsyscall_init(void *arg)
{
long cpu = (long)arg;
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
- smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 0, 1);
+ smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1);
return NOTIFY_DONE;
}
#ifdef CONFIG_SYSCTL
register_sysctl_table(kernel_root_table2);
#endif
- on_each_cpu(cpu_vsyscall_init, NULL, 0, 1);
+ on_each_cpu(cpu_vsyscall_init, NULL, 1);
hotcpu_notifier(cpu_vsyscall_notifier, 0);
return 0;
}
* activity count. Finally exported by i386_ksyms.c */
static int voyager_extended_cpus = 1;
-/* Have we found an SMP box - used by time.c to do the profiling
- interrupt for timeslicing; do not set to 1 until the per CPU timer
- interrupt is active */
-int smp_found_config = 0;
-
/* Used for the invalidate map that's also checked in the spinlock */
static volatile unsigned long smp_invalidate_needed;
halt();
}
- static DEFINE_SPINLOCK(call_lock);
-
- struct call_data_struct {
- void (*func) (void *info);
- void *info;
- volatile unsigned long started;
- volatile unsigned long finished;
- int wait;
- };
-
- static struct call_data_struct *call_data;
-
/* execute a thread on a new CPU. The function to be called must be
* previously set up. This is used to schedule a function for
* execution on all CPUs - set up the function then broadcast a
* function_interrupt CPI to come here on each CPU */
static void smp_call_function_interrupt(void)
{
- void (*func) (void *info) = call_data->func;
- void *info = call_data->info;
- /* must take copy of wait because call_data may be replaced
- * unless the function is waiting for us to finish */
- int wait = call_data->wait;
- __u8 cpu = smp_processor_id();
-
- /*
- * Notify initiating CPU that I've grabbed the data and am
- * about to execute the function
- */
- mb();
- if (!test_and_clear_bit(cpu, &call_data->started)) {
- /* If the bit wasn't set, this could be a replay */
- printk(KERN_WARNING "VOYAGER SMP: CPU %d received call funtion"
- " with no call pending\n", cpu);
- return;
- }
- /*
- * At this point the info structure may be out of scope unless wait==1
- */
irq_enter();
- (*func) (info);
+ generic_smp_call_function_interrupt();
__get_cpu_var(irq_stat).irq_call_count++;
irq_exit();
- if (wait) {
- mb();
- clear_bit(cpu, &call_data->finished);
- }
}
- static int
- voyager_smp_call_function_mask(cpumask_t cpumask,
- void (*func) (void *info), void *info, int wait)
+ static void smp_call_function_single_interrupt(void)
{
- struct call_data_struct data;
- u32 mask = cpus_addr(cpumask)[0];
-
- mask &= ~(1 << smp_processor_id());
-
- if (!mask)
- return 0;
-
- /* Can deadlock when called with interrupts disabled */
- WARN_ON(irqs_disabled());
-
- data.func = func;
- data.info = info;
- data.started = mask;
- data.wait = wait;
- if (wait)
- data.finished = mask;
-
- spin_lock(&call_lock);
- call_data = &data;
- wmb();
- /* Send a message to all other CPUs and wait for them to respond */
- send_CPI(mask, VIC_CALL_FUNCTION_CPI);
-
- /* Wait for response */
- while (data.started)
- barrier();
-
- if (wait)
- while (data.finished)
- barrier();
-
- spin_unlock(&call_lock);
-
- return 0;
+ irq_enter();
+ generic_smp_call_function_single_interrupt();
+ __get_cpu_var(irq_stat).irq_call_count++;
+ irq_exit();
}
/* Sorry about the name. In an APIC based system, the APICs
smp_call_function_interrupt();
}
+ void smp_qic_call_function_single_interrupt(struct pt_regs *regs)
+ {
+ ack_QIC_CPI(QIC_CALL_FUNCTION_SINGLE_CPI);
+ smp_call_function_single_interrupt();
+ }
+
void smp_vic_cpi_interrupt(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
smp_enable_irq_interrupt();
if (test_and_clear_bit(VIC_CALL_FUNCTION_CPI, &vic_cpi_mailbox[cpu]))
smp_call_function_interrupt();
+ if (test_and_clear_bit(VIC_CALL_FUNCTION_SINGLE_CPI, &vic_cpi_mailbox[cpu]))
+ smp_call_function_single_interrupt();
set_irq_regs(old_regs);
}
/* flush the TLB of every active CPU in the system */
void flush_tlb_all(void)
{
- on_each_cpu(do_flush_tlb_all, 0, 1, 1);
+ on_each_cpu(do_flush_tlb_all, 0, 1);
}
-/* used to set up the trampoline for other CPUs when the memory manager
- * is sorted out */
-void __init smp_alloc_memory(void)
-{
- trampoline_base = alloc_bootmem_low_pages(PAGE_SIZE);
- if (__pa(trampoline_base) >= 0x93000)
- BUG();
-}
-
/* send a reschedule CPI to one CPU by physical CPU number*/
static void voyager_smp_send_reschedule(int cpu)
{
/* broadcast a halt to all other CPUs */
static void voyager_smp_send_stop(void)
{
- smp_call_function(smp_stop_cpu_function, NULL, 1, 1);
+ smp_call_function(smp_stop_cpu_function, NULL, 1);
}
/* this function is triggered in time.c when a clock tick fires
.smp_send_stop = voyager_smp_send_stop,
.smp_send_reschedule = voyager_smp_send_reschedule,
- .smp_call_function_mask = voyager_smp_call_function_mask,
+
+ .send_call_func_ipi = native_send_call_func_ipi,
+ .send_call_func_single_ipi = native_send_call_func_single_ipi,
};
unsigned force_split : 1;
};
+#ifdef CONFIG_PROC_FS
+static unsigned long direct_pages_count[PG_LEVEL_NUM];
+
+void update_page_count(int level, unsigned long pages)
+{
+ unsigned long flags;
+
+ /* Protect against CPA */
+ spin_lock_irqsave(&pgd_lock, flags);
+ direct_pages_count[level] += pages;
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
+static void split_page_count(int level)
+{
+ direct_pages_count[level]--;
+ direct_pages_count[level - 1] += PTRS_PER_PTE;
+}
+
+int arch_report_meminfo(char *page)
+{
+ int n = sprintf(page, "DirectMap4k: %8lu\n"
+ "DirectMap2M: %8lu\n",
+ direct_pages_count[PG_LEVEL_4K],
+ direct_pages_count[PG_LEVEL_2M]);
+#ifdef CONFIG_X86_64
+ n += sprintf(page + n, "DirectMap1G: %8lu\n",
+ direct_pages_count[PG_LEVEL_1G]);
+#endif
+ return n;
+}
+#else
+static inline void split_page_count(int level) { }
+#endif
+
#ifdef CONFIG_X86_64
static inline unsigned long highmap_start_pfn(void)
{
BUG_ON(irqs_disabled());
- on_each_cpu(__cpa_flush_all, (void *) cache, 1, 1);
+ on_each_cpu(__cpa_flush_all, (void *) cache, 1);
}
static void __cpa_flush_range(void *arg)
BUG_ON(irqs_disabled());
WARN_ON(PAGE_ALIGN(start) != start);
- on_each_cpu(__cpa_flush_range, NULL, 1, 1);
+ on_each_cpu(__cpa_flush_range, NULL, 1);
if (!cache)
return;
return pte_offset_kernel(pmd, address);
}
+EXPORT_SYMBOL_GPL(lookup_address);
/*
* Set the new pmd in all the pgds we know about:
for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
+ if (address >= (unsigned long)__va(0) &&
+ address < (unsigned long)__va(max_low_pfn_mapped << PAGE_SHIFT))
+ split_page_count(level);
+
+#ifdef CONFIG_X86_64
+ if (address >= (unsigned long)__va(1UL<<32) &&
+ address < (unsigned long)__va(max_pfn_mapped << PAGE_SHIFT))
+ split_page_count(level);
+#endif
+
/*
* Install the new, split up pagetable. Important details here:
*
struct cpa_data alias_cpa;
int ret = 0;
- if (cpa->pfn > max_pfn_mapped)
+ if (cpa->pfn >= max_pfn_mapped)
return 0;
+#ifdef CONFIG_X86_64
+ if (cpa->pfn >= max_low_pfn_mapped && cpa->pfn < (1UL<<(32-PAGE_SHIFT)))
+ return 0;
+#endif
/*
* No need to redo, when the primary call touched the direct
* mapping already:
*/
- if (!within(cpa->vaddr, PAGE_OFFSET,
- PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) {
+ if (!(within(cpa->vaddr, PAGE_OFFSET,
+ PAGE_OFFSET + (max_low_pfn_mapped << PAGE_SHIFT))
+#ifdef CONFIG_X86_64
+ || within(cpa->vaddr, PAGE_OFFSET + (1UL<<32),
+ PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))
+#endif
+ )) {
alias_cpa = *cpa;
alias_cpa.vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
int set_memory_wc(unsigned long addr, int numpages)
{
- if (!pat_wc_enabled)
+ if (!pat_enabled)
return set_memory_uc(addr, numpages);
if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
}
}
- on_each_cpu(nmi_save_registers, NULL, 0, 1);
- on_each_cpu(nmi_cpu_setup, NULL, 0, 1);
+ on_each_cpu(nmi_save_registers, NULL, 1);
+ on_each_cpu(nmi_cpu_setup, NULL, 1);
nmi_enabled = 1;
return 0;
}
static void nmi_shutdown(void)
{
- struct op_msrs *msrs = &__get_cpu_var(cpu_msrs);
+ struct op_msrs *msrs = &get_cpu_var(cpu_msrs);
nmi_enabled = 0;
- on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
+ on_each_cpu(nmi_cpu_shutdown, NULL, 1);
unregister_die_notifier(&profile_exceptions_nb);
model->shutdown(msrs);
free_msrs();
+ put_cpu_var(cpu_msrs);
}
static void nmi_cpu_start(void *dummy)
static int nmi_start(void)
{
- on_each_cpu(nmi_cpu_start, NULL, 0, 1);
+ on_each_cpu(nmi_cpu_start, NULL, 1);
return 0;
}
static void nmi_stop(void)
{
- on_each_cpu(nmi_cpu_stop, NULL, 0, 1);
+ on_each_cpu(nmi_cpu_stop, NULL, 1);
}
struct op_counter_config counter_config[OP_MAX_COUNTER];
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/reboot.h>
+#include <asm/pgalloc.h>
#include "xen-ops.h"
#include "mmu.h"
struct start_info *xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);
-static /* __initdata */ struct shared_info dummy_shared_info;
+struct shared_info xen_dummy_shared_info;
/*
* Point at some empty memory to start with. We map the real shared_info
* page as soon as fixmap is up and running.
*/
-struct shared_info *HYPERVISOR_shared_info = (void *)&dummy_shared_info;
+struct shared_info *HYPERVISOR_shared_info = (void *)&xen_dummy_shared_info;
/*
* Flag to determine whether vcpu info placement is available on all
*/
static int have_vcpu_info_placement = 1;
-static void __init xen_vcpu_setup(int cpu)
+static void xen_vcpu_setup(int cpu)
{
struct vcpu_register_vcpu_info info;
int err;
struct vcpu_info *vcpup;
- BUG_ON(HYPERVISOR_shared_info == &dummy_shared_info);
+ BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
if (!have_vcpu_info_placement)
}
}
+/*
+ * On restore, set the vcpu placement up again.
+ * If it fails, then we're in a bad state, since
+ * we can't back out from using it...
+ */
+void xen_vcpu_restore(void)
+{
+ if (have_vcpu_info_placement) {
+ int cpu;
+
+ for_each_online_cpu(cpu) {
+ bool other_cpu = (cpu != smp_processor_id());
+
+ if (other_cpu &&
+ HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL))
+ BUG();
+
+ xen_vcpu_setup(cpu);
+
+ if (other_cpu &&
+ HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL))
+ BUG();
+ }
+
+ BUG_ON(!have_vcpu_info_placement);
+ }
+}
+
static void __init xen_banner(void)
{
printk(KERN_INFO "Booting paravirtualized kernel on %s\n",
pv_info.name);
- printk(KERN_INFO "Hypervisor signature: %s\n", xen_start_info->magic);
+ printk(KERN_INFO "Hypervisor signature: %s%s\n",
+ xen_start_info->magic,
+ xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
}
static void xen_cpuid(unsigned int *ax, unsigned int *bx,
{
struct vcpu_info *vcpu;
- /* There's a one instruction preempt window here. We need to
- make sure we're don't switch CPUs between getting the vcpu
- pointer and updating the mask. */
- preempt_disable();
+ /* We don't need to worry about being preempted here, since
+ either a) interrupts are disabled, so no preemption, or b)
+ the caller is confused and is trying to re-enable interrupts
+ on an indeterminate processor. */
+
vcpu = x86_read_percpu(xen_vcpu);
vcpu->evtchn_upcall_mask = 0;
- preempt_enable_no_resched();
/* Doesn't matter if we get preempted here, because any
pending event will get dealt with anyway. */
static void xen_safe_halt(void)
{
/* Blocking includes an implicit local_irq_enable(). */
- if (HYPERVISOR_sched_op(SCHEDOP_block, 0) != 0)
+ if (HYPERVISOR_sched_op(SCHEDOP_block, NULL) != 0)
BUG();
}
xen_mc_issue(PARAVIRT_LAZY_MMU);
}
+static void xen_clts(void)
+{
+ struct multicall_space mcs;
+
+ mcs = xen_mc_entry(0);
+
+ MULTI_fpu_taskswitch(mcs.mc, 0);
+
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
+static void xen_write_cr0(unsigned long cr0)
+{
+ struct multicall_space mcs;
+
+ /* Only pay attention to cr0.TS; everything else is
+ ignored. */
+ mcs = xen_mc_entry(0);
+
+ MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
+
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
+}
+
static void xen_write_cr2(unsigned long cr2)
{
x86_read_percpu(xen_vcpu)->arch.cr2 = cr2;
static void xen_write_cr4(unsigned long cr4)
{
- /* Just ignore cr4 changes; Xen doesn't allow us to do
- anything anyway. */
+ cr4 &= ~X86_CR4_PGE;
+ cr4 &= ~X86_CR4_PSE;
+
+ native_write_cr4(cr4);
}
static unsigned long xen_read_cr3(void)
PFN_DOWN(__pa(xen_start_info->pt_base)));
}
-static __init void setup_shared_info(void)
+void xen_setup_shared_info(void)
{
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
unsigned long addr = fix_to_virt(FIX_PARAVIRT_BOOTMAP);
/* In UP this is as good a place as any to set up shared info */
xen_setup_vcpu_info_placement();
#endif
+
+ xen_setup_mfn_list_list();
}
static __init void xen_pagetable_setup_done(pgd_t *base)
pv_mmu_ops.release_pmd = xen_release_pmd;
pv_mmu_ops.set_pte = xen_set_pte;
- setup_shared_info();
+ xen_setup_shared_info();
/* Actually pin the pagetable down, but we can't set PG_pinned
yet because the page structures don't exist yet. */
pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
}
+static __init void xen_post_allocator_init(void)
+{
+ pv_mmu_ops.set_pmd = xen_set_pmd;
+ pv_mmu_ops.set_pud = xen_set_pud;
+
+ xen_mark_init_mm_pinned();
+}
+
/* This is called once we have the cpu_possible_map */
-void __init xen_setup_vcpu_info_placement(void)
+void xen_setup_vcpu_info_placement(void)
{
int cpu;
return ret;
}
+static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot)
+{
+ pte_t pte;
+
+ phys >>= PAGE_SHIFT;
+
+ switch (idx) {
+ case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
+#ifdef CONFIG_X86_F00F_BUG
+ case FIX_F00F_IDT:
+#endif
+ case FIX_WP_TEST:
+ case FIX_VDSO:
+#ifdef CONFIG_X86_LOCAL_APIC
+ case FIX_APIC_BASE: /* maps dummy local APIC */
+#endif
+ pte = pfn_pte(phys, prot);
+ break;
+
+ default:
+ pte = mfn_pte(phys, prot);
+ break;
+ }
+
+ __native_set_fixmap(idx, pte);
+}
+
static const struct pv_info xen_info __initdata = {
.paravirt_enabled = 1,
.shared_kernel_pmd = 0,
.banner = xen_banner,
.memory_setup = xen_memory_setup,
.arch_setup = xen_arch_setup,
- .post_allocator_init = xen_mark_init_mm_pinned,
+ .post_allocator_init = xen_post_allocator_init,
};
static const struct pv_time_ops xen_time_ops __initdata = {
.set_wallclock = xen_set_wallclock,
.get_wallclock = xen_get_wallclock,
- .get_cpu_khz = xen_cpu_khz,
+ .get_tsc_khz = xen_tsc_khz,
.sched_clock = xen_sched_clock,
};
.set_debugreg = xen_set_debugreg,
.get_debugreg = xen_get_debugreg,
- .clts = native_clts,
+ .clts = xen_clts,
.read_cr0 = native_read_cr0,
- .write_cr0 = native_write_cr0,
+ .write_cr0 = xen_write_cr0,
.read_cr4 = native_read_cr4,
.read_cr4_safe = native_read_cr4_safe,
.read_pmc = native_read_pmc,
.iret = xen_iret,
- .irq_enable_syscall_ret = xen_sysexit,
+ .irq_enable_sysexit = xen_sysexit,
.load_tr_desc = paravirt_nop,
.set_ldt = xen_set_ldt,
.irq_enable = xen_irq_enable,
.safe_halt = xen_safe_halt,
.halt = xen_halt,
+#ifdef CONFIG_X86_64
+ .adjust_exception_frame = paravirt_nop,
+#endif
};
static const struct pv_apic_ops xen_apic_ops __initdata = {
.pte_update = paravirt_nop,
.pte_update_defer = paravirt_nop,
+ .pgd_alloc = __paravirt_pgd_alloc,
+ .pgd_free = paravirt_nop,
+
.alloc_pte = xen_alloc_pte_init,
.release_pte = xen_release_pte_init,
.alloc_pmd = xen_alloc_pte_init,
.set_pte = NULL, /* see xen_pagetable_setup_* */
.set_pte_at = xen_set_pte_at,
- .set_pmd = xen_set_pmd,
+ .set_pmd = xen_set_pmd_hyper,
+
+ .ptep_modify_prot_start = __ptep_modify_prot_start,
+ .ptep_modify_prot_commit = __ptep_modify_prot_commit,
.pte_val = xen_pte_val,
+ .pte_flags = native_pte_val,
.pgd_val = xen_pgd_val,
.make_pte = xen_make_pte,
.set_pte_atomic = xen_set_pte_atomic,
.set_pte_present = xen_set_pte_at,
- .set_pud = xen_set_pud,
+ .set_pud = xen_set_pud_hyper,
.pte_clear = xen_pte_clear,
.pmd_clear = xen_pmd_clear,
.enter = paravirt_enter_lazy_mmu,
.leave = xen_leave_lazy,
},
+
+ .set_fixmap = xen_set_fixmap,
};
#ifdef CONFIG_SMP
.smp_send_stop = xen_smp_send_stop,
.smp_send_reschedule = xen_smp_send_reschedule,
- .smp_call_function_mask = xen_smp_call_function_mask,
+
+ .send_call_func_ipi = xen_smp_send_call_function_ipi,
+ .send_call_func_single_ipi = xen_smp_send_call_function_single_ipi,
};
#endif /* CONFIG_SMP */
static void xen_reboot(int reason)
{
+ struct sched_shutdown r = { .reason = reason };
+
#ifdef CONFIG_SMP
smp_send_stop();
#endif
- if (HYPERVISOR_sched_op(SCHEDOP_shutdown, reason))
+ if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r))
BUG();
}
BUG_ON(memcmp(xen_start_info->magic, "xen-3", 5) != 0);
+ xen_setup_features();
+
/* Install Xen paravirt ops */
pv_info = xen_info;
pv_init_ops = xen_init_ops;
pv_apic_ops = xen_apic_ops;
pv_mmu_ops = xen_mmu_ops;
+ if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) {
+ pv_mmu_ops.ptep_modify_prot_start = xen_ptep_modify_prot_start;
+ pv_mmu_ops.ptep_modify_prot_commit = xen_ptep_modify_prot_commit;
+ }
+
machine_ops = xen_machine_ops;
#ifdef CONFIG_SMP
smp_ops = xen_smp_ops;
#endif
- xen_setup_features();
-
/* Get mfn list */
if (!xen_feature(XENFEAT_auto_translated_physmap))
- phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list;
+ xen_build_dynamic_phys_to_machine();
pgd = (pgd_t *)xen_start_info->pt_base;
+ init_pg_tables_start = __pa(pgd);
init_pg_tables_end = __pa(pgd) + xen_start_info->nr_pt_frames*PAGE_SIZE;
+ max_pfn_mapped = (init_pg_tables_end + 512*1024) >> PAGE_SHIFT;
init_mm.pgd = pgd; /* use the Xen pagetables to start */
? __pa(xen_start_info->mod_start) : 0;
boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
- if (!is_initial_xendomain())
+ if (!is_initial_xendomain()) {
+ add_preferred_console("xenboot", 0, NULL);
+ add_preferred_console("tty", 0, NULL);
add_preferred_console("hvc", 0, NULL);
+ }
/* Start the world */
- start_kernel();
+ i386_start_kernel();
}
#include "multicalls.h"
#include "mmu.h"
+#define P2M_ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(unsigned long))
+#define TOP_ENTRIES (MAX_DOMAIN_PAGES / P2M_ENTRIES_PER_PAGE)
+
+/* Placeholder for holes in the address space */
+static unsigned long p2m_missing[P2M_ENTRIES_PER_PAGE]
+ __attribute__((section(".data.page_aligned"))) =
+ { [ 0 ... P2M_ENTRIES_PER_PAGE-1 ] = ~0UL };
+
+ /* Array of pointers to pages containing p2m entries */
+static unsigned long *p2m_top[TOP_ENTRIES]
+ __attribute__((section(".data.page_aligned"))) =
+ { [ 0 ... TOP_ENTRIES - 1] = &p2m_missing[0] };
+
+/* Arrays of p2m arrays expressed in mfns used for save/restore */
+static unsigned long p2m_top_mfn[TOP_ENTRIES]
+ __attribute__((section(".bss.page_aligned")));
+
+static unsigned long p2m_top_mfn_list[
+ PAGE_ALIGN(TOP_ENTRIES / P2M_ENTRIES_PER_PAGE)]
+ __attribute__((section(".bss.page_aligned")));
+
+static inline unsigned p2m_top_index(unsigned long pfn)
+{
+ BUG_ON(pfn >= MAX_DOMAIN_PAGES);
+ return pfn / P2M_ENTRIES_PER_PAGE;
+}
+
+static inline unsigned p2m_index(unsigned long pfn)
+{
+ return pfn % P2M_ENTRIES_PER_PAGE;
+}
+
+/* Build the parallel p2m_top_mfn structures */
+void xen_setup_mfn_list_list(void)
+{
+ unsigned pfn, idx;
+
+ for(pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_ENTRIES_PER_PAGE) {
+ unsigned topidx = p2m_top_index(pfn);
+
+ p2m_top_mfn[topidx] = virt_to_mfn(p2m_top[topidx]);
+ }
+
+ for(idx = 0; idx < ARRAY_SIZE(p2m_top_mfn_list); idx++) {
+ unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
+ p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
+ }
+
+ BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
+
+ HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
+ virt_to_mfn(p2m_top_mfn_list);
+ HYPERVISOR_shared_info->arch.max_pfn = xen_start_info->nr_pages;
+}
+
+/* Set up p2m_top to point to the domain-builder provided p2m pages */
+void __init xen_build_dynamic_phys_to_machine(void)
+{
+ unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
+ unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
+ unsigned pfn;
+
+ for(pfn = 0; pfn < max_pfn; pfn += P2M_ENTRIES_PER_PAGE) {
+ unsigned topidx = p2m_top_index(pfn);
+
+ p2m_top[topidx] = &mfn_list[pfn];
+ }
+}
+
+unsigned long get_phys_to_machine(unsigned long pfn)
+{
+ unsigned topidx, idx;
+
+ if (unlikely(pfn >= MAX_DOMAIN_PAGES))
+ return INVALID_P2M_ENTRY;
+
+ topidx = p2m_top_index(pfn);
+ idx = p2m_index(pfn);
+ return p2m_top[topidx][idx];
+}
+EXPORT_SYMBOL_GPL(get_phys_to_machine);
+
+static void alloc_p2m(unsigned long **pp, unsigned long *mfnp)
+{
+ unsigned long *p;
+ unsigned i;
+
+ p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
+ BUG_ON(p == NULL);
+
+ for(i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
+ p[i] = INVALID_P2M_ENTRY;
+
+ if (cmpxchg(pp, p2m_missing, p) != p2m_missing)
+ free_page((unsigned long)p);
+ else
+ *mfnp = virt_to_mfn(p);
+}
+
+void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+ unsigned topidx, idx;
+
+ if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
+ BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+ return;
+ }
+
+ if (unlikely(pfn >= MAX_DOMAIN_PAGES)) {
+ BUG_ON(mfn != INVALID_P2M_ENTRY);
+ return;
+ }
+
+ topidx = p2m_top_index(pfn);
+ if (p2m_top[topidx] == p2m_missing) {
+ /* no need to allocate a page to store an invalid entry */
+ if (mfn == INVALID_P2M_ENTRY)
+ return;
+ alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]);
+ }
+
+ idx = p2m_index(pfn);
+ p2m_top[topidx][idx] = mfn;
+}
+
xmaddr_t arbitrary_virt_to_machine(unsigned long address)
{
unsigned int level;
}
-void xen_set_pmd(pmd_t *ptr, pmd_t val)
+static bool page_pinned(void *ptr)
+{
+ struct page *page = virt_to_page(ptr);
+
+ return PagePinned(page);
+}
+
+static void extend_mmu_update(const struct mmu_update *update)
{
struct multicall_space mcs;
struct mmu_update *u;
- preempt_disable();
+ mcs = xen_mc_extend_args(__HYPERVISOR_mmu_update, sizeof(*u));
+
+ if (mcs.mc != NULL)
+ mcs.mc->args[1]++;
+ else {
+ mcs = __xen_mc_entry(sizeof(*u));
+ MULTI_mmu_update(mcs.mc, mcs.args, 1, NULL, DOMID_SELF);
+ }
- mcs = xen_mc_entry(sizeof(*u));
u = mcs.args;
- u->ptr = virt_to_machine(ptr).maddr;
- u->val = pmd_val_ma(val);
- MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
+ *u = *update;
+}
+
+void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
+{
+ struct mmu_update u;
+
+ preempt_disable();
+
+ xen_mc_batch();
+
+ u.ptr = virt_to_machine(ptr).maddr;
+ u.val = pmd_val_ma(val);
+ extend_mmu_update(&u);
xen_mc_issue(PARAVIRT_LAZY_MMU);
preempt_enable();
}
+void xen_set_pmd(pmd_t *ptr, pmd_t val)
+{
+ /* If page is not pinned, we can just update the entry
+ directly */
+ if (!page_pinned(ptr)) {
+ *ptr = val;
+ return;
+ }
+
+ xen_set_pmd_hyper(ptr, val);
+}
+
/*
* Associate a virtual page frame with a given physical page frame
* and protection flags for that frame.
preempt_enable();
}
+pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+ /* Just return the pte as-is. We preserve the bits on commit */
+ return *ptep;
+}
+
+void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte)
+{
+ struct mmu_update u;
+
+ xen_mc_batch();
+
+ u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
+ u.val = pte_val_ma(pte);
+ extend_mmu_update(&u);
+
+ xen_mc_issue(PARAVIRT_LAZY_MMU);
+}
+
/* Assume pteval_t is equivalent to all the other *val_t types. */
static pteval_t pte_mfn_to_pfn(pteval_t val)
{
if (val & _PAGE_PRESENT) {
unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
pteval_t flags = val & ~PTE_MASK;
- val = (mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+ val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
}
return val;
if (val & _PAGE_PRESENT) {
unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
pteval_t flags = val & ~PTE_MASK;
- val = (pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
+ val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
}
return val;
return pte_mfn_to_pfn(pmd.pmd);
}
-void xen_set_pud(pud_t *ptr, pud_t val)
+void xen_set_pud_hyper(pud_t *ptr, pud_t val)
{
- struct multicall_space mcs;
- struct mmu_update *u;
+ struct mmu_update u;
preempt_disable();
- mcs = xen_mc_entry(sizeof(*u));
- u = mcs.args;
- u->ptr = virt_to_machine(ptr).maddr;
- u->val = pud_val_ma(val);
- MULTI_mmu_update(mcs.mc, u, 1, NULL, DOMID_SELF);
+ xen_mc_batch();
+
+ u.ptr = virt_to_machine(ptr).maddr;
+ u.val = pud_val_ma(val);
+ extend_mmu_update(&u);
xen_mc_issue(PARAVIRT_LAZY_MMU);
preempt_enable();
}
+void xen_set_pud(pud_t *ptr, pud_t val)
+{
+ /* If page is not pinned, we can just update the entry
+ directly */
+ if (!page_pinned(ptr)) {
+ *ptr = val;
+ return;
+ }
+
+ xen_set_pud_hyper(ptr, val);
+}
+
void xen_set_pte(pte_t *ptep, pte_t pte)
{
ptep->pte_high = pte.pte_high;
void xen_pmd_clear(pmd_t *pmdp)
{
- xen_set_pmd(pmdp, __pmd(0));
+ set_pmd(pmdp, __pmd(0));
}
pmd_t xen_make_pmd(pmdval_t pmd)
xen_mc_issue(0);
}
+/*
+ * On save, we need to pin all pagetables to make sure they get their
+ * mfns turned into pfns. Search the list for any unpinned pgds and pin
+ * them (unpinned pgds are not currently in use, probably because the
+ * process is under construction or destruction).
+ */
+void xen_mm_pin_all(void)
+{
+ unsigned long flags;
+ struct page *page;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+
+ list_for_each_entry(page, &pgd_list, lru) {
+ if (!PagePinned(page)) {
+ xen_pgd_pin((pgd_t *)page_address(page));
+ SetPageSavePinned(page);
+ }
+ }
+
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
/* The init_mm pagetable is really pinned as soon as its created, but
that's before we have page structures to store the bits. So do all
the book-keeping now. */
xen_mc_issue(0);
}
+/*
+ * On resume, undo any pinning done at save, so that the rest of the
+ * kernel doesn't see any unexpected pinned pagetables.
+ */
+void xen_mm_unpin_all(void)
+{
+ unsigned long flags;
+ struct page *page;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+
+ list_for_each_entry(page, &pgd_list, lru) {
+ if (PageSavePinned(page)) {
+ BUG_ON(!PagePinned(page));
+ printk("unpinning pinned %p\n", page_address(page));
+ xen_pgd_unpin((pgd_t *)page_address(page));
+ ClearPageSavePinned(page);
+ }
+ }
+
+ spin_unlock_irqrestore(&pgd_lock, flags);
+}
+
void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
{
spin_lock(&next->page_table_lock);
}
if (!cpus_empty(mask))
- xen_smp_call_function_mask(mask, drop_other_mm_ref, mm, 1);
+ smp_call_function_mask(mask, drop_other_mm_ref, mm, 1);
}
#else
static void drop_mm_ref(struct mm_struct *mm)
spin_lock(&mm->page_table_lock);
/* pgd may not be pinned in the error exit path of execve */
- if (PagePinned(virt_to_page(mm->pgd)))
+ if (page_pinned(mm->pgd))
xen_pgd_unpin(mm->pgd);
spin_unlock(&mm->page_table_lock);
#include "xen-ops.h"
#include "mmu.h"
-static cpumask_t xen_cpu_initialized_map;
+cpumask_t xen_cpu_initialized_map;
- static DEFINE_PER_CPU(int, resched_irq) = -1;
- static DEFINE_PER_CPU(int, callfunc_irq) = -1;
- static DEFINE_PER_CPU(int, debug_irq) = -1;
-
- /*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- */
- static DEFINE_SPINLOCK(call_lock);
- struct call_data_struct {
- void (*func) (void *info);
- void *info;
- atomic_t started;
- atomic_t finished;
- int wait;
- };
+ static DEFINE_PER_CPU(int, resched_irq);
+ static DEFINE_PER_CPU(int, callfunc_irq);
+ static DEFINE_PER_CPU(int, callfuncsingle_irq);
+ static DEFINE_PER_CPU(int, debug_irq) = -1;
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
-
- static struct call_data_struct *call_data;
+ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
/*
* Reschedule call back. Nothing to do,
*/
static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
{
+#ifdef CONFIG_X86_32
+ __get_cpu_var(irq_stat).irq_resched_count++;
+#else
+ add_pda(irq_resched_count, 1);
+#endif
+
return IRQ_HANDLED;
}
goto fail;
per_cpu(debug_irq, cpu) = rc;
+ callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+ rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
+ cpu,
+ xen_call_function_single_interrupt,
+ IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+ callfunc_name,
+ NULL);
+ if (rc < 0)
+ goto fail;
+ per_cpu(callfuncsingle_irq, cpu) = rc;
+
return 0;
fail:
unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
if (per_cpu(debug_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
+ if (per_cpu(callfuncsingle_irq, cpu) >= 0)
+ unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+
return rc;
}
void xen_smp_send_stop(void)
{
- smp_call_function(stop_self, NULL, 0, 0);
+ smp_call_function(stop_self, NULL, 0);
}
void xen_smp_send_reschedule(int cpu)
xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
}
-
static void xen_send_IPI_mask(cpumask_t mask, enum ipi_vector vector)
{
unsigned cpu;
xen_send_IPI_one(cpu, vector);
}
+ void xen_smp_send_call_function_ipi(cpumask_t mask)
+ {
+ int cpu;
+
+ xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
+
+ /* Make sure other vcpus get a chance to run if they need to. */
+ for_each_cpu_mask(cpu, mask) {
+ if (xen_vcpu_stolen(cpu)) {
+ HYPERVISOR_sched_op(SCHEDOP_yield, 0);
+ break;
+ }
+ }
+ }
+
+ void xen_smp_send_call_function_single_ipi(int cpu)
+ {
+ xen_send_IPI_mask(cpumask_of_cpu(cpu), XEN_CALL_FUNCTION_SINGLE_VECTOR);
+ }
+
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
{
- void (*func) (void *info) = call_data->func;
- void *info = call_data->info;
- int wait = call_data->wait;
-
- /*
- * Notify initiating CPU that I've grabbed the data and am
- * about to execute the function
- */
- mb();
- atomic_inc(&call_data->started);
- /*
- * At this point the info structure may be out of scope unless wait==1
- */
irq_enter();
- (*func)(info);
+ generic_smp_call_function_interrupt();
__get_cpu_var(irq_stat).irq_call_count++;
irq_exit();
- if (wait) {
- mb(); /* commit everything before setting finished */
- atomic_inc(&call_data->finished);
- }
-
return IRQ_HANDLED;
}
- int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
- void *info, int wait)
+ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
{
- struct call_data_struct data;
- int cpus, cpu;
- bool yield;
-
- /* Holding any lock stops cpus from going down. */
- spin_lock(&call_lock);
-
- cpu_clear(smp_processor_id(), mask);
-
- cpus = cpus_weight(mask);
- if (!cpus) {
- spin_unlock(&call_lock);
- return 0;
- }
-
- /* Can deadlock when called with interrupts disabled */
- WARN_ON(irqs_disabled());
-
- data.func = func;
- data.info = info;
- atomic_set(&data.started, 0);
- data.wait = wait;
- if (wait)
- atomic_set(&data.finished, 0);
-
- call_data = &data;
- mb(); /* write everything before IPI */
-
- /* Send a message to other CPUs and wait for them to respond */
- xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
-
- /* Make sure other vcpus get a chance to run if they need to. */
- yield = false;
- for_each_cpu_mask(cpu, mask)
- if (xen_vcpu_stolen(cpu))
- yield = true;
-
- if (yield)
- HYPERVISOR_sched_op(SCHEDOP_yield, 0);
-
- /* Wait for response */
- while (atomic_read(&data.started) != cpus ||
- (wait && atomic_read(&data.finished) != cpus))
- cpu_relax();
-
- spin_unlock(&call_lock);
+ irq_enter();
+ generic_smp_call_function_single_interrupt();
+ __get_cpu_var(irq_stat).irq_call_count++;
+ irq_exit();
- return 0;
+ return IRQ_HANDLED;
}
extern const char xen_hypervisor_callback[];
extern const char xen_failsafe_callback[];
+struct trap_info;
void xen_copy_trap_info(struct trap_info *traps);
DECLARE_PER_CPU(unsigned long, xen_cr3);
DECLARE_PER_CPU(unsigned long, xen_current_cr3);
extern struct start_info *xen_start_info;
+extern struct shared_info xen_dummy_shared_info;
extern struct shared_info *HYPERVISOR_shared_info;
+void xen_setup_mfn_list_list(void);
+void xen_setup_shared_info(void);
+
char * __init xen_memory_setup(void);
void __init xen_arch_setup(void);
void __init xen_init_IRQ(void);
void xen_enable_sysenter(void);
+void xen_vcpu_restore(void);
+
+void __init xen_build_dynamic_phys_to_machine(void);
void xen_setup_timer(int cpu);
void xen_setup_cpu_clockevents(void);
-unsigned long xen_cpu_khz(void);
+unsigned long xen_tsc_khz(void);
void __init xen_time_init(void);
unsigned long xen_get_wallclock(void);
int xen_set_wallclock(unsigned long time);
unsigned long long xen_sched_clock(void);
+void xen_timer_resume(void);
irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
void xen_smp_send_stop(void);
void xen_smp_send_reschedule(int cpu);
- int xen_smp_call_function (void (*func) (void *info), void *info, int nonatomic,
- int wait);
- int xen_smp_call_function_single(int cpu, void (*func) (void *info), void *info,
- int nonatomic, int wait);
-
- int xen_smp_call_function_mask(cpumask_t mask, void (*func)(void *),
- void *info, int wait);
+ void xen_smp_send_call_function_ipi(cpumask_t mask);
+ void xen_smp_send_call_function_single_ipi(int cpu);
+extern cpumask_t xen_cpu_initialized_map;
+
/* Declare an asm function, along with symbols needed to make it
inlineable */
* contents - it is a noop if I/O is still in
* flight on potentially older contents.
*/
- ll_rw_block(SWRITE, 1, &bh);
+ ll_rw_block(SWRITE_SYNC, 1, &bh);
brelse(bh);
spin_lock(lock);
}
void invalidate_bh_lrus(void)
{
- on_each_cpu(invalidate_bh_lru, NULL, 1, 1);
+ on_each_cpu(invalidate_bh_lru, NULL, 1);
}
EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
*/
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
- } else if (!buffer_mapped(bh) && buffer_dirty(bh)) {
+ } else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
+ buffer_dirty(bh)) {
WARN_ON(bh->b_size != blocksize);
err = get_block(inode, block, bh, 1);
if (err)
goto recover;
+ clear_buffer_delay(bh);
if (buffer_new(bh)) {
/* blockdev mappings never come here */
clear_buffer_new(bh);
bh = head;
/* Recovery: lock and submit the mapped buffers */
do {
- if (buffer_mapped(bh) && buffer_dirty(bh)) {
+ if (buffer_mapped(bh) && buffer_dirty(bh) &&
+ !buffer_delay(bh)) {
lock_buffer(bh);
mark_buffer_async_write(bh);
} else {
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
+ int i_size_changed = 0;
copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
*/
if (pos+copied > inode->i_size) {
i_size_write(inode, pos+copied);
- mark_inode_dirty(inode);
+ i_size_changed = 1;
}
unlock_page(page);
page_cache_release(page);
+ /*
+ * Don't mark the inode dirty under page lock. First, it unnecessarily
+ * makes the holding time of page lock longer. Second, it forces lock
+ * ordering of page lock and transaction start for journaling
+ * filesystems.
+ */
+ if (i_size_changed)
+ mark_inode_dirty(inode);
+
return copied;
}
EXPORT_SYMBOL(generic_write_end);
for (i = 0; i < nr; i++) {
struct buffer_head *bh = bhs[i];
- if (rw == SWRITE)
+ if (rw == SWRITE || rw == SWRITE_SYNC)
lock_buffer(bh);
else if (test_set_buffer_locked(bh))
continue;
- if (rw == WRITE || rw == SWRITE) {
+ if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC) {
if (test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
get_bh(bh);
- submit_bh(WRITE, bh);
+ if (rw == SWRITE_SYNC)
+ submit_bh(WRITE_SYNC, bh);
+ else
+ submit_bh(WRITE, bh);
continue;
}
} else {
if (test_clear_buffer_dirty(bh)) {
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(WRITE, bh);
+ ret = submit_bh(WRITE_SYNC, bh);
wait_on_buffer(bh);
if (buffer_eopnotsupp(bh)) {
clear_buffer_eopnotsupp(bh);
+#ifndef _ASM_HW_IRQ_H
+#define _ASM_HW_IRQ_H
+
+/*
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * moved some of the old arch/i386/kernel/irq.h to here. VY
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@informatik.tu-chemnitz.de>
+ *
+ * hacked by Andi Kleen for x86-64.
+ * unified by tglx
+ */
+
+#include <asm/irq_vectors.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/smp.h>
+
+#include <asm/atomic.h>
+#include <asm/irq.h>
+#include <asm/sections.h>
+
+#define platform_legacy_irq(irq) ((irq) < 16)
+
+/* Interrupt handlers registered during init_IRQ */
+extern void apic_timer_interrupt(void);
+extern void error_interrupt(void);
+extern void spurious_interrupt(void);
+extern void thermal_interrupt(void);
+extern void reschedule_interrupt(void);
+
+extern void invalidate_interrupt(void);
+extern void invalidate_interrupt0(void);
+extern void invalidate_interrupt1(void);
+extern void invalidate_interrupt2(void);
+extern void invalidate_interrupt3(void);
+extern void invalidate_interrupt4(void);
+extern void invalidate_interrupt5(void);
+extern void invalidate_interrupt6(void);
+extern void invalidate_interrupt7(void);
+
+extern void irq_move_cleanup_interrupt(void);
+extern void threshold_interrupt(void);
+
+extern void call_function_interrupt(void);
++extern void call_function_single_interrupt(void);
+
+/* PIC specific functions */
+extern void disable_8259A_irq(unsigned int irq);
+extern void enable_8259A_irq(unsigned int irq);
+extern int i8259A_irq_pending(unsigned int irq);
+extern void make_8259A_irq(unsigned int irq);
+extern void init_8259A(int aeoi);
+
+/* IOAPIC */
+#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
+extern unsigned long io_apic_irqs;
+
+extern void init_VISWS_APIC_irqs(void);
+extern void setup_IO_APIC(void);
+extern void disable_IO_APIC(void);
+extern void print_IO_APIC(void);
+extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
+extern void setup_ioapic_dest(void);
+
+#ifdef CONFIG_X86_64
+extern void enable_IO_APIC(void);
+#endif
+
+/* IPI functions */
+extern void send_IPI_self(int vector);
+extern void send_IPI(int dest, int vector);
+
+/* Statistics */
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
+
+/* EISA */
+extern void eisa_set_level_irq(unsigned int irq);
+
+/* Voyager functions */
+extern asmlinkage void vic_cpi_interrupt(void);
+extern asmlinkage void vic_sys_interrupt(void);
+extern asmlinkage void vic_cmn_interrupt(void);
+extern asmlinkage void qic_timer_interrupt(void);
+extern asmlinkage void qic_invalidate_interrupt(void);
+extern asmlinkage void qic_reschedule_interrupt(void);
+extern asmlinkage void qic_enable_irq_interrupt(void);
+extern asmlinkage void qic_call_function_interrupt(void);
+
#ifdef CONFIG_X86_32
-# include "hw_irq_32.h"
+extern void (*const interrupt[NR_IRQS])(void);
#else
-# include "hw_irq_64.h"
+typedef int vector_irq_t[NR_VECTORS];
+DECLARE_PER_CPU(vector_irq_t, vector_irq);
+extern spinlock_t vector_lock;
+#endif
+extern void setup_vector_irq(int cpu);
+
+#endif /* !ASSEMBLY_ */
+
#endif
--- /dev/null
- #define VIC_END_FAKE_CPI VIC_CALL_FUNCTION_CPI
+#ifndef _ASM_IRQ_VECTORS_H
+#define _ASM_IRQ_VECTORS_H
+
+#include <linux/threads.h>
+
+#define NMI_VECTOR 0x02
+
+/*
+ * IDT vectors usable for external interrupt sources start
+ * at 0x20:
+ */
+#define FIRST_EXTERNAL_VECTOR 0x20
+
+#ifdef CONFIG_X86_32
+# define SYSCALL_VECTOR 0x80
+#else
+# define IA32_SYSCALL_VECTOR 0x80
+#endif
+
+/*
+ * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
+ * cleanup after irq migration on 64 bit.
+ */
+#define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR
+
+/*
+ * Vectors 0x20-0x2f are used for ISA interrupts on 32 bit.
+ * Vectors 0x30-0x3f are used for ISA interrupts on 64 bit.
+ */
+#ifdef CONFIG_X86_32
+#define IRQ0_VECTOR (FIRST_EXTERNAL_VECTOR)
+#else
+#define IRQ0_VECTOR (FIRST_EXTERNAL_VECTOR + 0x10)
+#endif
+#define IRQ1_VECTOR (IRQ0_VECTOR + 1)
+#define IRQ2_VECTOR (IRQ0_VECTOR + 2)
+#define IRQ3_VECTOR (IRQ0_VECTOR + 3)
+#define IRQ4_VECTOR (IRQ0_VECTOR + 4)
+#define IRQ5_VECTOR (IRQ0_VECTOR + 5)
+#define IRQ6_VECTOR (IRQ0_VECTOR + 6)
+#define IRQ7_VECTOR (IRQ0_VECTOR + 7)
+#define IRQ8_VECTOR (IRQ0_VECTOR + 8)
+#define IRQ9_VECTOR (IRQ0_VECTOR + 9)
+#define IRQ10_VECTOR (IRQ0_VECTOR + 10)
+#define IRQ11_VECTOR (IRQ0_VECTOR + 11)
+#define IRQ12_VECTOR (IRQ0_VECTOR + 12)
+#define IRQ13_VECTOR (IRQ0_VECTOR + 13)
+#define IRQ14_VECTOR (IRQ0_VECTOR + 14)
+#define IRQ15_VECTOR (IRQ0_VECTOR + 15)
+
+/*
+ * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
+ *
+ * some of the following vectors are 'rare', they are merged
+ * into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
+ * TLB, reschedule and local APIC vectors are performance-critical.
+ *
+ * Vectors 0xf0-0xfa are free (reserved for future Linux use).
+ */
+#ifdef CONFIG_X86_32
+
+# define SPURIOUS_APIC_VECTOR 0xff
+# define ERROR_APIC_VECTOR 0xfe
+# define INVALIDATE_TLB_VECTOR 0xfd
+# define RESCHEDULE_VECTOR 0xfc
+# define CALL_FUNCTION_VECTOR 0xfb
++# define CALL_FUNCTION_SINGLE_VECTOR 0xfa
+# define THERMAL_APIC_VECTOR 0xf0
+
+#else
+
+#define SPURIOUS_APIC_VECTOR 0xff
+#define ERROR_APIC_VECTOR 0xfe
+#define RESCHEDULE_VECTOR 0xfd
+#define CALL_FUNCTION_VECTOR 0xfc
++#define CALL_FUNCTION_SINGLE_VECTOR 0xfb
+#define THERMAL_APIC_VECTOR 0xfa
+#define THRESHOLD_APIC_VECTOR 0xf9
+#define INVALIDATE_TLB_VECTOR_END 0xf7
+#define INVALIDATE_TLB_VECTOR_START 0xf0 /* f0-f7 used for TLB flush */
+
+#define NUM_INVALIDATE_TLB_VECTORS 8
+
+#endif
+
+/*
+ * Local APIC timer IRQ vector is on a different priority level,
+ * to work around the 'lost local interrupt if more than 2 IRQ
+ * sources per level' errata.
+ */
+#define LOCAL_TIMER_VECTOR 0xef
+
+/*
+ * First APIC vector available to drivers: (vectors 0x30-0xee) we
+ * start at 0x31(0x41) to spread out vectors evenly between priority
+ * levels. (0x80 is the syscall vector)
+ */
+#ifdef CONFIG_X86_32
+# define FIRST_DEVICE_VECTOR 0x31
+#else
+# define FIRST_DEVICE_VECTOR (IRQ15_VECTOR + 2)
+#endif
+
+#define NR_VECTORS 256
+
+#define FPU_IRQ 13
+
+#define FIRST_VM86_IRQ 3
+#define LAST_VM86_IRQ 15
+#define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15)
+
+#if !defined(CONFIG_X86_VOYAGER)
+
+# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
+
+# define NR_IRQS 224
+
+# if (224 >= 32 * NR_CPUS)
+# define NR_IRQ_VECTORS NR_IRQS
+# else
+# define NR_IRQ_VECTORS (32 * NR_CPUS)
+# endif
+
+# else /* IO_APIC || PARAVIRT */
+
+# define NR_IRQS 16
+# define NR_IRQ_VECTORS NR_IRQS
+
+# endif
+
+#else /* !VISWS && !VOYAGER */
+
+# define NR_IRQS 224
+# define NR_IRQ_VECTORS NR_IRQS
+
+#endif /* VISWS */
+
+/* Voyager specific defines */
+/* These define the CPIs we use in linux */
+#define VIC_CPI_LEVEL0 0
+#define VIC_CPI_LEVEL1 1
+/* now the fake CPIs */
+#define VIC_TIMER_CPI 2
+#define VIC_INVALIDATE_CPI 3
+#define VIC_RESCHEDULE_CPI 4
+#define VIC_ENABLE_IRQ_CPI 5
+#define VIC_CALL_FUNCTION_CPI 6
++#define VIC_CALL_FUNCTION_SINGLE_CPI 7
+
+/* Now the QIC CPIs: Since we don't need the two initial levels,
+ * these are 2 less than the VIC CPIs */
+#define QIC_CPI_OFFSET 1
+#define QIC_TIMER_CPI (VIC_TIMER_CPI - QIC_CPI_OFFSET)
+#define QIC_INVALIDATE_CPI (VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
+#define QIC_RESCHEDULE_CPI (VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
+#define QIC_ENABLE_IRQ_CPI (VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_CPI (VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
++#define QIC_CALL_FUNCTION_SINGLE_CPI (VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
+
+#define VIC_START_FAKE_CPI VIC_TIMER_CPI
++#define VIC_END_FAKE_CPI VIC_CALL_FUNCTION_SINGLE_CPI
+
+/* this is the SYS_INT CPI. */
+#define VIC_SYS_INT 8
+#define VIC_CMN_INT 15
+
+/* This is the boot CPI for alternate processors. It gets overwritten
+ * by the above once the system has activated all available processors */
+#define VIC_CPU_BOOT_CPI VIC_CPI_LEVEL0
+#define VIC_CPU_BOOT_ERRATA_CPI (VIC_CPI_LEVEL0 + 8)
+
+
+#endif /* _ASM_IRQ_VECTORS_H */
extern unsigned int num_processors;
extern cpumask_t cpu_initialized;
-#ifdef CONFIG_SMP
-extern u16 x86_cpu_to_apicid_init[];
-extern u16 x86_bios_cpu_apicid_init[];
-extern void *x86_cpu_to_apicid_early_ptr;
-extern void *x86_bios_cpu_apicid_early_ptr;
-#else
-#define x86_cpu_to_apicid_early_ptr NULL
-#define x86_bios_cpu_apicid_early_ptr NULL
-#endif
-
DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
DECLARE_PER_CPU(cpumask_t, cpu_core_map);
DECLARE_PER_CPU(u16, cpu_llc_id);
-DECLARE_PER_CPU(u16, x86_cpu_to_apicid);
-DECLARE_PER_CPU(u16, x86_bios_cpu_apicid);
+
+DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
/* Static state in head.S used to set up a CPU */
extern struct {
void (*smp_send_stop)(void);
void (*smp_send_reschedule)(int cpu);
- int (*smp_call_function_mask)(cpumask_t mask,
- void (*func)(void *info), void *info,
- int wait);
+
+ void (*send_call_func_ipi)(cpumask_t mask);
+ void (*send_call_func_single_ipi)(int cpu);
};
/* Globals due to paravirt */
smp_ops.smp_send_reschedule(cpu);
}
- static inline int smp_call_function_mask(cpumask_t mask,
- void (*func) (void *info), void *info,
- int wait)
+ static inline void arch_send_call_function_single_ipi(int cpu)
+ {
+ smp_ops.send_call_func_single_ipi(cpu);
+ }
+
+ static inline void arch_send_call_function_ipi(cpumask_t mask)
{
- return smp_ops.smp_call_function_mask(mask, func, info, wait);
+ smp_ops.send_call_func_ipi(mask);
}
void native_smp_prepare_boot_cpu(void);
void native_smp_prepare_cpus(unsigned int max_cpus);
void native_smp_cpus_done(unsigned int max_cpus);
int native_cpu_up(unsigned int cpunum);
+ void native_send_call_func_ipi(cpumask_t mask);
+ void native_send_call_func_single_ipi(int cpu);
extern int __cpu_disable(void);
extern void __cpu_die(unsigned int cpu);
-extern void prefill_possible_map(void);
-
void smp_store_cpu_info(int id);
#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu)
}
#endif /* CONFIG_SMP */
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_CPU)
+extern void prefill_possible_map(void);
+#else
+static inline void prefill_possible_map(void)
+{
+}
+#endif
+
extern unsigned disabled_cpus __cpuinitdata;
#ifdef CONFIG_X86_32_SMP
#endif /* CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_HOTPLUG_CPU
-extern void cpu_exit_clear(void);
extern void cpu_uninit(void);
#endif
- extern void lock_ipi_call_lock(void);
- extern void unlock_ipi_call_lock(void);
-extern void smp_alloc_memory(void);
#endif /* __ASSEMBLY__ */
#endif
#
obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
- exit.o itimer.o time.o softirq.o resource.o \
+ cpu.o exit.o itimer.o time.o softirq.o resource.o \
sysctl.o capability.o ptrace.o timer.o user.o \
signal.o sys.o kmod.o workqueue.o pid.o \
rcupdate.o extable.o params.o posix-timers.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
notifier.o ksysfs.o pm_qos_params.o sched_clock.o
+CFLAGS_REMOVE_sched.o = -mno-spe
+
+ifdef CONFIG_FTRACE
+# Do not trace debug files and internal ftrace files
+CFLAGS_REMOVE_lockdep.o = -pg
+CFLAGS_REMOVE_lockdep_proc.o = -pg
+CFLAGS_REMOVE_mutex-debug.o = -pg
+CFLAGS_REMOVE_rtmutex-debug.o = -pg
+CFLAGS_REMOVE_cgroup-debug.o = -pg
+CFLAGS_REMOVE_sched_clock.o = -pg
+endif
+
obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += time/
obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
-obj-$(CONFIG_SMP) += cpu.o spinlock.o
+ obj-$(CONFIG_USE_GENERIC_SMP_HELPERS) += smp.o
+obj-$(CONFIG_SMP) += spinlock.o
obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
obj-$(CONFIG_UID16) += uid16.o
obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
obj-$(CONFIG_MARKERS) += marker.o
obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_FTRACE) += trace/
+obj-$(CONFIG_TRACING) += trace/
+obj-$(CONFIG_SMP) += sched_cpupri.o
ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
*/
u64 ktime_divns(const ktime_t kt, s64 div)
{
- u64 dclc, inc, dns;
+ u64 dclc;
int sft = 0;
- dclc = dns = ktime_to_ns(kt);
- inc = div;
+ dclc = ktime_to_ns(kt);
/* Make sure the divisor is less than 2^32: */
while (div >> 32) {
sft++;
void clock_was_set(void)
{
/* Retrigger the CPU local events everywhere */
- on_each_cpu(retrigger_next_event, NULL, 0, 1);
+ on_each_cpu(retrigger_next_event, NULL, 1);
}
/*
*/
void hres_timers_resume(void)
{
- WARN_ON_ONCE(num_online_cpus() > 1);
-
/* Retrigger the CPU local events: */
retrigger_next_event(NULL);
}
*/
raise = timer->state == HRTIMER_STATE_PENDING;
+ /*
+ * We use preempt_disable to prevent this task from migrating after
+ * setting up the softirq and raising it. Otherwise, if me migrate
+ * we will raise the softirq on the wrong CPU.
+ */
+ preempt_disable();
+
unlock_hrtimer_base(timer, &flags);
if (raise)
hrtimer_raise_softirq();
+ preempt_enable();
return ret;
}
}
EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
-#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ)
+#ifdef CONFIG_NO_HZ
/**
* hrtimer_get_next_event - get the time until next expiry event
*
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
#ifdef CONFIG_HIGH_RES_TIMERS
- open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq, NULL);
+ open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
#endif
}
EXPORT_SYMBOL(_local_bh_enable);
-void local_bh_enable(void)
+static inline void _local_bh_enable_ip(unsigned long ip)
{
+ WARN_ON_ONCE(in_irq() || irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
- unsigned long flags;
-
- WARN_ON_ONCE(in_irq());
-#endif
- WARN_ON_ONCE(irqs_disabled());
-
-#ifdef CONFIG_TRACE_IRQFLAGS
- local_irq_save(flags);
+ local_irq_disable();
#endif
/*
* Are softirqs going to be turned on now:
*/
if (softirq_count() == SOFTIRQ_OFFSET)
- trace_softirqs_on((unsigned long)__builtin_return_address(0));
+ trace_softirqs_on(ip);
/*
* Keep preemption disabled until we are done with
* softirq processing:
dec_preempt_count();
#ifdef CONFIG_TRACE_IRQFLAGS
- local_irq_restore(flags);
+ local_irq_enable();
#endif
preempt_check_resched();
}
+
+void local_bh_enable(void)
+{
+ _local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+}
EXPORT_SYMBOL(local_bh_enable);
void local_bh_enable_ip(unsigned long ip)
{
-#ifdef CONFIG_TRACE_IRQFLAGS
- unsigned long flags;
-
- WARN_ON_ONCE(in_irq());
-
- local_irq_save(flags);
-#endif
- /*
- * Are softirqs going to be turned on now:
- */
- if (softirq_count() == SOFTIRQ_OFFSET)
- trace_softirqs_on(ip);
- /*
- * Keep preemption disabled until we are done with
- * softirq processing:
- */
- sub_preempt_count(SOFTIRQ_OFFSET - 1);
-
- if (unlikely(!in_interrupt() && local_softirq_pending()))
- do_softirq();
-
- dec_preempt_count();
-#ifdef CONFIG_TRACE_IRQFLAGS
- local_irq_restore(flags);
-#endif
- preempt_check_resched();
+ _local_bh_enable_ip(ip);
}
EXPORT_SYMBOL(local_bh_enable_ip);
local_irq_restore(flags);
}
-void open_softirq(int nr, void (*action)(struct softirq_action*), void *data)
+void open_softirq(int nr, void (*action)(struct softirq_action *))
{
- softirq_vec[nr].data = data;
softirq_vec[nr].action = action;
}
struct tasklet_struct **tail;
};
-/* Some compilers disobey section attribute on statics when not
- initialized -- RR */
-static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec) = { NULL };
-static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec) = { NULL };
+static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
+static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);
void __tasklet_schedule(struct tasklet_struct *t)
{
&per_cpu(tasklet_hi_vec, cpu).head;
}
- open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
- open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
+ open_softirq(TASKLET_SOFTIRQ, tasklet_action);
+ open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}
static int ksoftirqd(void * __bind_cpu)
p = per_cpu(ksoftirqd, hotcpu);
per_cpu(ksoftirqd, hotcpu) = NULL;
- sched_setscheduler(p, SCHED_FIFO, ¶m);
+ sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m);
kthread_stop(p);
takeover_tasklets(hotcpu);
break;
/*
* Call a function on all processors
*/
- int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait)
+ int on_each_cpu(void (*func) (void *info), void *info, int wait)
{
int ret = 0;
preempt_disable();
- ret = smp_call_function(func, info, retry, wait);
+ ret = smp_call_function(func, info, wait);
local_irq_disable();
func(info);
local_irq_enable();
struct tick_device tick_broadcast_device;
static cpumask_t tick_broadcast_mask;
static DEFINE_SPINLOCK(tick_broadcast_lock);
+static int tick_broadcast_force;
#ifdef CONFIG_TICK_ONESHOT
static void tick_broadcast_clear_oneshot(int cpu);
CLOCK_EVT_MODE_SHUTDOWN);
}
if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE)
- dev->features |= CLOCK_EVT_FEAT_DUMMY;
+ tick_broadcast_force = 1;
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
- if (cpu_isset(cpu, tick_broadcast_mask)) {
+ if (!tick_broadcast_force &&
+ cpu_isset(cpu, tick_broadcast_mask)) {
cpu_clear(cpu, tick_broadcast_mask);
if (td->mode == TICKDEV_MODE_PERIODIC)
tick_setup_periodic(dev, 0);
"offline CPU #%d\n", *oncpu);
else
smp_call_function_single(*oncpu, tick_do_broadcast_on_off,
- &reason, 1, 1);
+ &reason, 1);
}
/*
*/
void drain_all_pages(void)
{
- on_each_cpu(drain_local_pages, NULL, 0, 1);
+ on_each_cpu(drain_local_pages, NULL, 1);
}
#ifdef CONFIG_HIBERNATION
static void build_zonelist_cache(pg_data_t *pgdat)
{
pgdat->node_zonelists[0].zlcache_ptr = NULL;
- pgdat->node_zonelists[1].zlcache_ptr = NULL;
}
#endif /* CONFIG_NUMA */
}
}
+void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
+{
+ int i;
+ int ret;
+
+ for_each_active_range_index_in_nid(i, nid) {
+ ret = work_fn(early_node_map[i].start_pfn,
+ early_node_map[i].end_pfn, data);
+ if (ret)
+ break;
+ }
+}
/**
* sparse_memory_present_with_active_regions - Call memory_present for each active range
* @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
calculate_node_totalpages(pgdat, zones_size, zholes_size);
alloc_node_mem_map(pgdat);
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+ printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n",
+ nid, (unsigned long)pgdat,
+ (unsigned long)pgdat->node_mem_map);
+#endif
free_area_init_core(pgdat, zones_size, zholes_size);
}
{
int i;
- printk(KERN_DEBUG "Entering add_active_range(%d, %lu, %lu) "
+ printk(KERN_DEBUG "Entering add_active_range(%d, %#lx, %#lx) "
"%d entries of %d used\n",
nid, start_pfn, end_pfn,
nr_nodemap_entries, MAX_ACTIVE_REGIONS);
}
/**
- * shrink_active_range - Shrink an existing registered range of PFNs
+ * remove_active_range - Shrink an existing registered range of PFNs
* @nid: The node id the range is on that should be shrunk
- * @old_end_pfn: The old end PFN of the range
- * @new_end_pfn: The new PFN of the range
+ * @start_pfn: The new PFN of the range
+ * @end_pfn: The new PFN of the range
*
* i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
- * The map is kept at the end physical page range that has already been
- * registered with add_active_range(). This function allows an arch to shrink
- * an existing registered range.
+ * The map is kept near the end physical page range that has already been
+ * registered. This function allows an arch to shrink an existing registered
+ * range.
*/
-void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
- unsigned long new_end_pfn)
+void __init remove_active_range(unsigned int nid, unsigned long start_pfn,
+ unsigned long end_pfn)
{
- int i;
+ int i, j;
+ int removed = 0;
+
+ printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n",
+ nid, start_pfn, end_pfn);
/* Find the old active region end and shrink */
- for_each_active_range_index_in_nid(i, nid)
- if (early_node_map[i].end_pfn == old_end_pfn) {
- early_node_map[i].end_pfn = new_end_pfn;
- break;
+ for_each_active_range_index_in_nid(i, nid) {
+ if (early_node_map[i].start_pfn >= start_pfn &&
+ early_node_map[i].end_pfn <= end_pfn) {
+ /* clear it */
+ early_node_map[i].start_pfn = 0;
+ early_node_map[i].end_pfn = 0;
+ removed = 1;
+ continue;
+ }
+ if (early_node_map[i].start_pfn < start_pfn &&
+ early_node_map[i].end_pfn > start_pfn) {
+ unsigned long temp_end_pfn = early_node_map[i].end_pfn;
+ early_node_map[i].end_pfn = start_pfn;
+ if (temp_end_pfn > end_pfn)
+ add_active_range(nid, end_pfn, temp_end_pfn);
+ continue;
}
+ if (early_node_map[i].start_pfn >= start_pfn &&
+ early_node_map[i].end_pfn > end_pfn &&
+ early_node_map[i].start_pfn < end_pfn) {
+ early_node_map[i].start_pfn = end_pfn;
+ continue;
+ }
+ }
+
+ if (!removed)
+ return;
+
+ /* remove the blank ones */
+ for (i = nr_nodemap_entries - 1; i > 0; i--) {
+ if (early_node_map[i].nid != nid)
+ continue;
+ if (early_node_map[i].end_pfn)
+ continue;
+ /* we found it, get rid of it */
+ for (j = i; j < nr_nodemap_entries - 1; j++)
+ memcpy(&early_node_map[j], &early_node_map[j+1],
+ sizeof(early_node_map[j]));
+ j = nr_nodemap_entries - 1;
+ memset(&early_node_map[j], 0, sizeof(early_node_map[j]));
+ nr_nodemap_entries--;
+ }
}
/**
}
/* Find the lowest pfn for a node */
-unsigned long __init find_min_pfn_for_node(unsigned long nid)
+unsigned long __init find_min_pfn_for_node(int nid)
{
int i;
unsigned long min_pfn = ULONG_MAX;
if (min_pfn == ULONG_MAX) {
printk(KERN_WARNING
- "Could not find start_pfn for node %lu\n", nid);
+ "Could not find start_pfn for node %d\n", nid);
return 0;
}
for (i = 0; i < MAX_NR_ZONES; i++) {
if (i == ZONE_MOVABLE)
continue;
- printk(" %-8s %8lu -> %8lu\n",
+ printk(" %-8s %0#10lx -> %0#10lx\n",
zone_names[i],
arch_zone_lowest_possible_pfn[i],
arch_zone_highest_possible_pfn[i]);
/* Print out the early_node_map[] */
printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
for (i = 0; i < nr_nodemap_entries; i++)
- printk(" %3d: %8lu -> %8lu\n", early_node_map[i].nid,
+ printk(" %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid,
early_node_map[i].start_pfn,
early_node_map[i].end_pfn);
#endif
#if DEBUG
-/**
- * slab_destroy_objs - destroy a slab and its objects
- * @cachep: cache pointer being destroyed
- * @slabp: slab pointer being destroyed
- *
- * Call the registered destructor for each object in a slab that is being
- * destroyed.
- */
-static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
{
int i;
for (i = 0; i < cachep->num; i++) {
}
}
#else
-static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
{
}
#endif
{
void *addr = slabp->s_mem - slabp->colouroff;
- slab_destroy_objs(cachep, slabp);
+ slab_destroy_debugcheck(cachep, slabp);
if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
struct slab_rcu *slab_rcu;
struct kmem_list3 *l3;
int node;
- on_each_cpu(do_drain, cachep, 1, 1);
+ on_each_cpu(do_drain, cachep, 1);
check_irq_on();
for_each_online_node(node) {
l3 = cachep->nodelists[node];
}
new->cachep = cachep;
- on_each_cpu(do_ccupdate_local, (void *)new, 1, 1);
+ on_each_cpu(do_ccupdate_local, (void *)new, 1);
check_irq_on();
cachep->batchcount = batchcount;
* The allocator synchronizes using per slab locks and only
* uses a centralized lock to manage a pool of partial slabs.
*
- * (C) 2007 SGI, Christoph Lameter <clameter@sgi.com>
+ * (C) 2007 SGI, Christoph Lameter
*/
#include <linux/mm.h>
if (addr) {
p->addr = addr;
p->cpu = smp_processor_id();
- p->pid = current ? current->pid : -1;
+ p->pid = current->pid;
p->when = jiffies;
} else
memset(p, 0, sizeof(struct track));
if (!t->addr)
return;
- printk(KERN_ERR "INFO: %s in ", s);
- __print_symbol("%s", (unsigned long)t->addr);
- printk(" age=%lu cpu=%u pid=%d\n", jiffies - t->when, t->cpu, t->pid);
+ printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n",
+ s, t->addr, jiffies - t->when, t->cpu, t->pid);
}
static void print_tracking(struct kmem_cache *s, void *object)
static void flush_all(struct kmem_cache *s)
{
#ifdef CONFIG_SMP
- on_each_cpu(flush_cpu_slab, s, 1, 1);
+ on_each_cpu(flush_cpu_slab, s, 1);
#else
unsigned long flags;
void **object;
struct kmem_cache_cpu *c;
unsigned long flags;
+ unsigned int objsize;
local_irq_save(flags);
c = get_cpu_slab(s, smp_processor_id());
+ objsize = c->objsize;
if (unlikely(!c->freelist || !node_match(c, node)))
object = __slab_alloc(s, gfpflags, node, addr, c);
local_irq_restore(flags);
if (unlikely((gfpflags & __GFP_ZERO) && object))
- memset(object, 0, c->objsize);
+ memset(object, 0, objsize);
return object;
}
page = virt_to_head_page(x);
if (unlikely(!PageSlab(page))) {
+ BUG_ON(!PageCompound(page));
put_page(page);
return;
}
create_kmalloc_cache(&kmalloc_caches[1],
"kmalloc-96", 96, GFP_KERNEL);
caches++;
- }
- if (KMALLOC_MIN_SIZE <= 128) {
create_kmalloc_cache(&kmalloc_caches[2],
"kmalloc-192", 192, GFP_KERNEL);
caches++;
for (i = 8; i < KMALLOC_MIN_SIZE; i += 8)
size_index[(i - 1) / 8] = KMALLOC_SHIFT_LOW;
+ if (KMALLOC_MIN_SIZE == 128) {
+ /*
+ * The 192 byte sized cache is not used if the alignment
+ * is 128 byte. Redirect kmalloc to use the 256 byte cache
+ * instead.
+ */
+ for (i = 128 + 8; i <= 192; i += 8)
+ size_index[(i - 1) / 8] = 8;
+ }
+
slab_state = UP;
/* Provide the correct kmalloc names now that the caches are up */
if (cpu_isset(cpu, iucv_buffer_cpumask) &&
!cpu_isset(cpu, iucv_irq_cpumask))
smp_call_function_single(cpu, iucv_allow_cpu,
- NULL, 0, 1);
+ NULL, 1);
preempt_enable();
}
cpumask = iucv_irq_cpumask;
cpu_clear(first_cpu(iucv_irq_cpumask), cpumask);
for_each_cpu_mask(cpu, cpumask)
- smp_call_function_single(cpu, iucv_block_cpu, NULL, 0, 1);
+ smp_call_function_single(cpu, iucv_block_cpu, NULL, 1);
}
/**
rc = -EIO;
preempt_disable();
for_each_online_cpu(cpu)
- smp_call_function_single(cpu, iucv_declare_cpu, NULL, 0, 1);
+ smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1);
preempt_enable();
if (cpus_empty(iucv_buffer_cpumask))
/* No cpu could declare an iucv buffer. */
*/
static void iucv_disable(void)
{
- on_each_cpu(iucv_retrieve_cpu, NULL, 0, 1);
+ on_each_cpu(iucv_retrieve_cpu, NULL, 1);
kfree(iucv_path_table);
}
case CPU_ONLINE_FROZEN:
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
- smp_call_function_single(cpu, iucv_declare_cpu, NULL, 0, 1);
+ smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
if (cpus_empty(cpumask))
/* Can't offline last IUCV enabled cpu. */
return NOTIFY_BAD;
- smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 0, 1);
+ smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 1);
if (cpus_empty(iucv_irq_cpumask))
smp_call_function_single(first_cpu(iucv_buffer_cpumask),
- iucv_allow_cpu, NULL, 0, 1);
+ iucv_allow_cpu, NULL, 1);
break;
}
return NOTIFY_OK;
* pending interrupts force them to the work queue by calling
* an empty function on all cpus.
*/
- smp_call_function(__iucv_cleanup_queue, NULL, 0, 1);
+ smp_call_function(__iucv_cleanup_queue, NULL, 1);
spin_lock_irq(&iucv_queue_lock);
list_for_each_entry_safe(p, n, &iucv_task_queue, list) {
/* Remove stale work items from the task queue. */
p = iucv_irq_data[smp_processor_id()];
if (p->ippathid >= iucv_max_pathid) {
- printk(KERN_WARNING "iucv_do_int: Got interrupt with "
- "pathid %d > max_connections (%ld)\n",
- p->ippathid, iucv_max_pathid - 1);
+ WARN_ON(p->ippathid >= iucv_max_pathid);
iucv_sever_pathid(p->ippathid, iucv_error_no_listener);
return;
}
- if (p->iptype < 0x01 || p->iptype > 0x09) {
- printk(KERN_ERR "iucv_do_int: unknown iucv interrupt\n");
- return;
- }
+ BUG_ON(p->iptype < 0x01 || p->iptype > 0x09);
work = kmalloc(sizeof(struct iucv_irq_list), GFP_ATOMIC);
if (!work) {
printk(KERN_WARNING "iucv_external_interrupt: out of memory\n");