git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks into timers/core
Frederic sayed: "Most of these patches have been hanging around for
several month now, in -mmotm for a significant chunk. They already
missed a few releases."
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
select GENERIC_PCI_IOMAP
+ select GENERIC_SCHED_CLOCK
select GENERIC_SMP_IDLE_THREAD
select GENERIC_IDLE_POLL_SETUP
select GENERIC_STRNCPY_FROM_USER
source "arch/arm/Kconfig-nommu"
endif
+ config PJ4B_ERRATA_4742
+ bool "PJ4B Errata 4742: IDLE Wake Up Commands can Cause the CPU Core to Cease Operation"
+ depends on CPU_PJ4B && MACH_ARMADA_370
+ default y
+ help
+ When coming out of either a Wait for Interrupt (WFI) or a Wait for
+ Event (WFE) IDLE states, a specific timing sensitivity exists between
+ the retiring WFI/WFE instructions and the newly issued subsequent
+ instructions. This sensitivity can result in a CPU hang scenario.
+ Workaround:
+ The software must insert either a Data Synchronization Barrier (DSB)
+ or Data Memory Barrier (DMB) command immediately after the WFI/WFE
+ instruction
+
config ARM_ERRATA_326103
bool "ARM errata: FSR write bit incorrect on a SWP to read-only memory"
depends on CPU_V6
is not correctly implemented in PL310 as clean lines are not
invalidated as a result of these operations.
+ config ARM_ERRATA_643719
+ bool "ARM errata: LoUIS bit field in CLIDR register is incorrect"
+ depends on CPU_V7 && SMP
+ help
+ This option enables the workaround for the 643719 Cortex-A9 (prior to
+ r1p0) erratum. On affected cores the LoUIS bit field of the CLIDR
+ register returns zero when it should return one. The workaround
+ corrects this value, ensuring cache maintenance operations which use
+ it behave as intended and avoiding data corruption.
+
config ARM_ERRATA_720789
bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
depends on CPU_V7
config KEXEC
bool "Kexec system call (EXPERIMENTAL)"
- depends on (!SMP || HOTPLUG_CPU)
+ depends on (!SMP || PM_SLEEP_SMP)
help
kexec is a system call that implements the ability to shutdown your
current kernel, and to start another kernel. It is like a reboot
* have elapsed since the hypervisor wrote the data. So we try to account for
* that with system time
*/
-static unsigned long kvm_get_wallclock(void)
+static void kvm_get_wallclock(struct timespec *now)
{
struct pvclock_vcpu_time_info *vcpu_time;
- struct timespec ts;
int low, high;
int cpu;
cpu = smp_processor_id();
vcpu_time = &hv_clock[cpu].pvti;
- pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
+ pvclock_read_wallclock(&wall_clock, vcpu_time, now);
preempt_enable();
-
- return ts.tv_sec;
}
-static int kvm_set_wallclock(unsigned long now)
+static int kvm_set_wallclock(const struct timespec *now)
{
return -1;
}
if (!mem)
return;
hv_clock = __va(mem);
+ memset(hv_clock, 0, size);
if (kvm_register_clock("boot clock")) {
hv_clock = NULL;
#include <linux/io.h>
#include <linux/reboot.h>
#include <linux/bcd.h>
- #include <linux/ucs2_string.h>
#include <asm/setup.h>
#include <asm/efi.h>
#define EFI_DEBUG 1
- /*
- * There's some additional metadata associated with each
- * variable. Intel's reference implementation is 60 bytes - bump that
- * to account for potential alignment constraints
- */
- #define VAR_METADATA_SIZE 64
+ #define EFI_MIN_RESERVE 5120
+
+ #define EFI_DUMMY_GUID \
+ EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
+
+ static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
struct efi __read_mostly efi = {
.mps = EFI_INVALID_TABLE_ADDR,
static struct efi efi_phys __initdata;
static efi_system_table_t efi_systab __initdata;
- static u64 efi_var_store_size;
- static u64 efi_var_remaining_size;
- static u64 efi_var_max_var_size;
- static u64 boot_used_size;
- static u64 boot_var_size;
- static u64 active_size;
-
unsigned long x86_efi_facility;
/*
efi_char16_t *name,
efi_guid_t *vendor)
{
- efi_status_t status;
- static bool finished = false;
- static u64 var_size;
-
- status = efi_call_virt3(get_next_variable,
- name_size, name, vendor);
-
- if (status == EFI_NOT_FOUND) {
- finished = true;
- if (var_size < boot_used_size) {
- boot_var_size = boot_used_size - var_size;
- active_size += boot_var_size;
- } else {
- printk(KERN_WARNING FW_BUG "efi: Inconsistent initial sizes\n");
- }
- }
-
- if (boot_used_size && !finished) {
- unsigned long size;
- u32 attr;
- efi_status_t s;
- void *tmp;
-
- s = virt_efi_get_variable(name, vendor, &attr, &size, NULL);
-
- if (s != EFI_BUFFER_TOO_SMALL || !size)
- return status;
-
- tmp = kmalloc(size, GFP_ATOMIC);
-
- if (!tmp)
- return status;
-
- s = virt_efi_get_variable(name, vendor, &attr, &size, tmp);
-
- if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) {
- var_size += size;
- var_size += ucs2_strsize(name, 1024);
- active_size += size;
- active_size += VAR_METADATA_SIZE;
- active_size += ucs2_strsize(name, 1024);
- }
-
- kfree(tmp);
- }
-
- return status;
+ return efi_call_virt3(get_next_variable,
+ name_size, name, vendor);
}
static efi_status_t virt_efi_set_variable(efi_char16_t *name,
unsigned long data_size,
void *data)
{
- efi_status_t status;
- u32 orig_attr = 0;
- unsigned long orig_size = 0;
-
- status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size,
- NULL);
-
- if (status != EFI_BUFFER_TOO_SMALL)
- orig_size = 0;
-
- status = efi_call_virt5(set_variable,
- name, vendor, attr,
- data_size, data);
-
- if (status == EFI_SUCCESS) {
- if (orig_size) {
- active_size -= orig_size;
- active_size -= ucs2_strsize(name, 1024);
- active_size -= VAR_METADATA_SIZE;
- }
- if (data_size) {
- active_size += data_size;
- active_size += ucs2_strsize(name, 1024);
- active_size += VAR_METADATA_SIZE;
- }
- }
-
- return status;
+ return efi_call_virt5(set_variable,
+ name, vendor, attr,
+ data_size, data);
}
static efi_status_t virt_efi_query_variable_info(u32 attr,
return status;
}
-int efi_set_rtc_mmss(unsigned long nowtime)
+int efi_set_rtc_mmss(const struct timespec *now)
{
+ unsigned long nowtime = now->tv_sec;
efi_status_t status;
efi_time_t eft;
efi_time_cap_t cap;
return 0;
}
-unsigned long efi_get_time(void)
+void efi_get_time(struct timespec *now)
{
efi_status_t status;
efi_time_t eft;
if (status != EFI_SUCCESS)
pr_err("Oops: efitime: can't read time!\n");
- return mktime(eft.year, eft.month, eft.day, eft.hour,
- eft.minute, eft.second);
+ now->tv_sec = mktime(eft.year, eft.month, eft.day, eft.hour,
+ eft.minute, eft.second);
+ now->tv_nsec = 0;
}
/*
char vendor[100] = "unknown";
int i = 0;
void *tmp;
- struct setup_data *data;
- struct efi_var_bootdata *efi_var_data;
- u64 pa_data;
#ifdef CONFIG_X86_32
if (boot_params.efi_info.efi_systab_hi ||
if (efi_systab_init(efi_phys.systab))
return;
- pa_data = boot_params.hdr.setup_data;
- while (pa_data) {
- data = early_ioremap(pa_data, sizeof(*efi_var_data));
- if (data->type == SETUP_EFI_VARS) {
- efi_var_data = (struct efi_var_bootdata *)data;
-
- efi_var_store_size = efi_var_data->store_size;
- efi_var_remaining_size = efi_var_data->remaining_size;
- efi_var_max_var_size = efi_var_data->max_var_size;
- }
- pa_data = data->next;
- early_iounmap(data, sizeof(*efi_var_data));
- }
-
- boot_used_size = efi_var_store_size - efi_var_remaining_size;
-
set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
/*
runtime_code_page_mkexec();
kfree(new_memmap);
+
+ /* clean DUMMY object */
+ efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+ EFI_VARIABLE_NON_VOLATILE |
+ EFI_VARIABLE_BOOTSERVICE_ACCESS |
+ EFI_VARIABLE_RUNTIME_ACCESS,
+ 0, NULL);
}
/*
efi_status_t status;
u64 storage_size, remaining_size, max_size;
+ if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
+ return 0;
+
status = efi.query_variable_info(attributes, &storage_size,
&remaining_size, &max_size);
if (status != EFI_SUCCESS)
return status;
- if (!max_size && remaining_size > size)
- printk_once(KERN_ERR FW_BUG "Broken EFI implementation"
- " is returning MaxVariableSize=0\n");
/*
* Some firmware implementations refuse to boot if there's insufficient
* space in the variable store. We account for that by refusing the
* write if permitting it would reduce the available space to under
- * 50%. However, some firmware won't reclaim variable space until
- * after the used (not merely the actively used) space drops below
- * a threshold. We can approximate that case with the value calculated
- * above. If both the firmware and our calculations indicate that the
- * available space would drop below 50%, refuse the write.
+ * 5KB. This figure was provided by Samsung, so should be safe.
*/
+ if ((remaining_size - size < EFI_MIN_RESERVE) &&
+ !efi_no_storage_paranoia) {
+
+ /*
+ * Triggering garbage collection may require that the firmware
+ * generate a real EFI_OUT_OF_RESOURCES error. We can force
+ * that by attempting to use more space than is available.
+ */
+ unsigned long dummy_size = remaining_size + 1024;
+ void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
+
+ if (!dummy)
+ return EFI_OUT_OF_RESOURCES;
+
+ status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+ EFI_VARIABLE_NON_VOLATILE |
+ EFI_VARIABLE_BOOTSERVICE_ACCESS |
+ EFI_VARIABLE_RUNTIME_ACCESS,
+ dummy_size, dummy);
+
+ if (status == EFI_SUCCESS) {
+ /*
+ * This should have failed, so if it didn't make sure
+ * that we delete it...
+ */
+ efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+ EFI_VARIABLE_NON_VOLATILE |
+ EFI_VARIABLE_BOOTSERVICE_ACCESS |
+ EFI_VARIABLE_RUNTIME_ACCESS,
+ 0, dummy);
+ }
+
+ kfree(dummy);
- if (!storage_size || size > remaining_size ||
- (max_size && size > max_size))
- return EFI_OUT_OF_RESOURCES;
+ /*
+ * The runtime code may now have triggered a garbage collection
+ * run, so check the variable info again
+ */
+ status = efi.query_variable_info(attributes, &storage_size,
+ &remaining_size, &max_size);
- if (!efi_no_storage_paranoia &&
- ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) &&
- (remaining_size - size < storage_size / 2)))
- return EFI_OUT_OF_RESOURCES;
+ if (status != EFI_SUCCESS)
+ return status;
+
+ /*
+ * There still isn't enough room, so return an error
+ */
+ if (remaining_size - size < EFI_MIN_RESERVE)
+ return EFI_OUT_OF_RESOURCES;
+ }
return EFI_SUCCESS;
}
config TREE_RCU
bool "Tree-based hierarchical RCU"
depends on !PREEMPT && SMP
+ select IRQ_WORK
help
This option selects the RCU implementation that is
designed for very large SMP system with hundreds or
config HAVE_UNSTABLE_SCHED_CLOCK
bool
+config GENERIC_SCHED_CLOCK
+ bool
+
#
# For architectures that want to enable the support for NUMA-affine scheduler
# balancing logic:
#include <linux/profile.h>
#include <linux/sched.h>
#include <linux/smp.h>
+#include <linux/module.h>
#include "tick-internal.h"
static struct tick_device tick_broadcast_device;
static cpumask_var_t tick_broadcast_mask;
+static cpumask_var_t tick_broadcast_on;
static cpumask_var_t tmpmask;
static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
static int tick_broadcast_force;
/*
* Check, if the device can be utilized as broadcast device:
*/
-int tick_check_broadcast_device(struct clock_event_device *dev)
+static bool tick_check_broadcast_device(struct clock_event_device *curdev,
+ struct clock_event_device *newdev)
+{
+ if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) ||
+ (newdev->features & CLOCK_EVT_FEAT_C3STOP))
+ return false;
+
+ if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT &&
+ !(newdev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return false;
+
+ return !curdev || newdev->rating > curdev->rating;
+}
+
+/*
+ * Conditionally install/replace broadcast device
+ */
+void tick_install_broadcast_device(struct clock_event_device *dev)
{
struct clock_event_device *cur = tick_broadcast_device.evtdev;
- if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
- (tick_broadcast_device.evtdev &&
- tick_broadcast_device.evtdev->rating >= dev->rating) ||
- (dev->features & CLOCK_EVT_FEAT_C3STOP))
- return 0;
+ if (!tick_check_broadcast_device(cur, dev))
+ return;
- clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+ if (!try_module_get(dev->owner))
+ return;
+
+ clockevents_exchange_device(cur, dev);
if (cur)
cur->event_handler = clockevents_handle_noop;
tick_broadcast_device.evtdev = dev;
*/
if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
tick_clock_notify();
- return 1;
}
/*
*/
int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
unsigned long flags;
- int ret = 0;
+ int ret;
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
dev->event_handler = tick_handle_periodic;
tick_device_setup_broadcast_func(dev);
cpumask_set_cpu(cpu, tick_broadcast_mask);
- tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
+ tick_broadcast_start_periodic(bc);
ret = 1;
} else {
/*
- * When the new device is not affected by the stop
- * feature and the cpu is marked in the broadcast mask
- * then clear the broadcast bit.
+ * Clear the broadcast bit for this cpu if the
+ * device is not power state affected.
*/
- if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
- int cpu = smp_processor_id();
+ if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
cpumask_clear_cpu(cpu, tick_broadcast_mask);
- tick_broadcast_clear_oneshot(cpu);
- } else {
+ else
tick_device_setup_broadcast_func(dev);
+
+ /*
+ * Clear the broadcast bit if the CPU is not in
+ * periodic broadcast on state.
+ */
+ if (!cpumask_test_cpu(cpu, tick_broadcast_on))
+ cpumask_clear_cpu(cpu, tick_broadcast_mask);
+
+ switch (tick_broadcast_device.mode) {
+ case TICKDEV_MODE_ONESHOT:
+ /*
+ * If the system is in oneshot mode we can
+ * unconditionally clear the oneshot mask bit,
+ * because the CPU is running and therefore
+ * not in an idle state which causes the power
+ * state affected device to stop. Let the
+ * caller initialize the device.
+ */
+ tick_broadcast_clear_oneshot(cpu);
+ ret = 0;
+ break;
+
+ case TICKDEV_MODE_PERIODIC:
+ /*
+ * If the system is in periodic mode, check
+ * whether the broadcast device can be
+ * switched off now.
+ */
+ if (cpumask_empty(tick_broadcast_mask) && bc)
+ clockevents_shutdown(bc);
+ /*
+ * If we kept the cpu in the broadcast mask,
+ * tell the caller to leave the per cpu device
+ * in shutdown state. The periodic interrupt
+ * is delivered by the broadcast device.
+ */
+ ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
+ break;
+ default:
+ /* Nothing to do */
+ ret = 0;
+ break;
}
}
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
switch (*reason) {
case CLOCK_EVT_NOTIFY_BROADCAST_ON:
case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
+ cpumask_set_cpu(cpu, tick_broadcast_on);
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
tick_broadcast_force = 1;
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
- if (!tick_broadcast_force &&
- cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
+ if (tick_broadcast_force)
+ break;
+ cpumask_clear_cpu(cpu, tick_broadcast_on);
+ if (!tick_device_is_functional(dev))
+ break;
+ if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
tick_setup_periodic(dev, 0);
bc = tick_broadcast_device.evtdev;
cpumask_clear_cpu(cpu, tick_broadcast_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_on);
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
if (bc && cpumask_empty(tick_broadcast_mask))
if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
- clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
+ /*
+ * We might be in the middle of switching over from
+ * periodic to oneshot. If the CPU has not yet
+ * switched over, leave the device alone.
+ */
+ if (td->mode == TICKDEV_MODE_ONESHOT) {
+ clockevents_set_mode(td->evtdev,
+ CLOCK_EVT_MODE_ONESHOT);
+ }
}
}
}
}
+ /*
+ * Remove the current cpu from the pending mask. The event is
+ * delivered immediately in tick_do_broadcast() !
+ */
+ cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask);
+
/* Take care of enforced broadcast requests */
cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask);
cpumask_clear(tick_broadcast_force_mask);
/*
+ * Sanity check. Catch the case where we try to broadcast to
+ * offline cpus.
+ */
+ if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask)))
+ cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+ /*
* Wakeup the cpus which have an expired event.
*/
tick_do_broadcast(tmpmask);
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
- WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
+ WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
/*
* We only reprogram the broadcast timer if we
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
- if (dev->next_event.tv64 == KTIME_MAX)
- goto out;
/*
* The cpu which was handling the broadcast
* timer marked this cpu in the broadcast
goto out;
/*
+ * Bail out if there is no next event.
+ */
+ if (dev->next_event.tv64 == KTIME_MAX)
+ goto out;
+ /*
* If the pending bit is not set, then we are
* either the CPU handling the broadcast
* interrupt or we got woken by something else.
bc->event_handler = tick_handle_oneshot_broadcast;
- /* Take the do_timer update */
- if (!tick_nohz_full_cpu(cpu))
- tick_do_timer_cpu = cpu;
-
/*
* We must be careful here. There might be other CPUs
* waiting for periodic broadcast. We need to set the
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
/*
- * Clear the broadcast mask flag for the dead cpu, but do not
- * stop the broadcast device!
+ * Clear the broadcast masks for the dead cpu, but do not stop
+ * the broadcast device!
*/
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
void __init tick_broadcast_init(void)
{
zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT);
zalloc_cpumask_var(&tmpmask, GFP_NOWAIT);
#ifdef CONFIG_TICK_ONESHOT
zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
#include "tick-internal.h"
#include "ntp_internal.h"
+#include "timekeeping_internal.h"
+
+#define TK_CLEAR_NTP (1 << 0)
+#define TK_MIRROR (1 << 1)
+#define TK_CLOCK_WAS_SET (1 << 2)
static struct timekeeper timekeeper;
static DEFINE_RAW_SPINLOCK(timekeeper_lock);
static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
-static void update_pvclock_gtod(struct timekeeper *tk)
+static void update_pvclock_gtod(struct timekeeper *tk, bool was_set)
{
- raw_notifier_call_chain(&pvclock_gtod_chain, 0, tk);
+ raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk);
}
/**
raw_spin_lock_irqsave(&timekeeper_lock, flags);
ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
- update_pvclock_gtod(tk);
+ update_pvclock_gtod(tk, true);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
return ret;
EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
/* must hold timekeeper_lock */
-static void timekeeping_update(struct timekeeper *tk, bool clearntp, bool mirror)
+static void timekeeping_update(struct timekeeper *tk, unsigned int action)
{
- if (clearntp) {
+ if (action & TK_CLEAR_NTP) {
tk->ntp_error = 0;
ntp_clear();
}
update_vsyscall(tk);
- update_pvclock_gtod(tk);
+ update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
- if (mirror)
+ if (action & TK_MIRROR)
memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
}
tk_set_xtime(tk, tv);
- timekeeping_update(tk, true, true);
+ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts));
error: /* even if we error out, we forwarded the time, so call update */
- timekeeping_update(tk, true, true);
+ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
- if (!new->enable || new->enable(new) == 0) {
- old = tk->clock;
- tk_setup_internals(tk, new);
- if (old->disable)
- old->disable(old);
+ /*
+ * If the cs is in module, get a module reference. Succeeds
+ * for built-in code (owner == NULL) as well.
+ */
+ if (try_module_get(new->owner)) {
+ if (!new->enable || new->enable(new) == 0) {
+ old = tk->clock;
+ tk_setup_internals(tk, new);
+ if (old->disable)
+ old->disable(old);
+ module_put(old->owner);
+ } else {
+ module_put(new->owner);
+ }
}
- timekeeping_update(tk, true, true);
+ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
* This function is called from clocksource.c after a new, better clock
* source has been registered. The caller holds the clocksource_mutex.
*/
-void timekeeping_notify(struct clocksource *clock)
+int timekeeping_notify(struct clocksource *clock)
{
struct timekeeper *tk = &timekeeper;
if (tk->clock == clock)
- return;
+ return 0;
stop_machine(change_clocksource, clock, NULL);
tick_clock_notify();
+ return tk->clock == clock ? 0 : -1;
}
/**
tk_xtime_add(tk, delta);
tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta));
tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta));
+ tk_debug_account_sleep_time(delta);
}
/**
__timekeeping_inject_sleeptime(tk, delta);
- timekeeping_update(tk, true, true);
+ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
tk->cycle_last = clock->cycle_last = cycle_now;
tk->ntp_error = 0;
timekeeping_suspended = 0;
- timekeeping_update(tk, false, true);
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
read_persistent_clock(&timekeeping_suspend_time);
+ /*
+ * On some systems the persistent_clock can not be detected at
+ * timekeeping_init by its return value, so if we see a valid
+ * value returned, update the persistent_clock_exists flag.
+ */
+ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
+ persistent_clock_exist = true;
+
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
* It also calls into the NTP code to handle leapsecond processing.
*
*/
-static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
+static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
+ unsigned int action = 0;
while (tk->xtime_nsec >= nsecps) {
int leap;
__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
clock_was_set_delayed();
+ action = TK_CLOCK_WAS_SET;
}
}
+ return action;
}
/**
struct timekeeper *tk = &shadow_timekeeper;
cycle_t offset;
int shift = 0, maxshift;
+ unsigned int action;
unsigned long flags;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
* Finally, make sure that after the rounding
* xtime_nsec isn't larger than NSEC_PER_SEC
*/
- accumulate_nsecs_to_secs(tk);
+ action = accumulate_nsecs_to_secs(tk);
write_seqcount_begin(&timekeeper_seq);
/* Update clock->cycle_last with the new value */
* updating.
*/
memcpy(real_tk, tk, sizeof(*tk));
- timekeeping_update(real_tk, false, false);
+ timekeeping_update(real_tk, action);
write_seqcount_end(&timekeeper_seq);
out:
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
if (tai != orig_tai) {
__timekeeping_set_tai_offset(tk, tai);
+ update_pvclock_gtod(tk, true);
clock_was_set_delayed();
}
write_seqcount_end(&timekeeper_seq);