search for: clocksource_mask

...hile (unlikely(lguest_data.time.tv_sec != sec)); + return sec*1000000000ULL + nsec; } /* This is what we tell the kernel is our clocksource. */ @@ -361,6 +370,8 @@ static struct clocksource lguest_clock = .name = "lguest", .rating = 400, .read = lguest_clock_read, + .mask = CLOCKSOURCE_MASK(64), + .mult = 1, }; static unsigned long long lguest_sched_clock(void) @@ -430,22 +441,17 @@ static void lguest_time_init(void) { set_irq_handler(0, lguest_time_irq); - /* We use the TSC if the Host tells us we can, otherwise a dumb - * jiffies-based clock. */ + /* We use the TSC if the...

...hile (unlikely(lguest_data.time.tv_sec != sec)); + return sec*1000000000ULL + nsec; } /* This is what we tell the kernel is our clocksource. */ @@ -361,6 +370,8 @@ static struct clocksource lguest_clock = .name = "lguest", .rating = 400, .read = lguest_clock_read, + .mask = CLOCKSOURCE_MASK(64), + .mult = 1, }; static unsigned long long lguest_sched_clock(void) @@ -430,22 +441,17 @@ static void lguest_time_init(void) { set_irq_handler(0, lguest_time_irq); - /* We use the TSC if the Host tells us we can, otherwise a dumb - * jiffies-based clock. */ + /* We use the TSC if the...

Lguest currently requires a TSC, which breaks older machines and Matt Mackall who boots the host with "notsc". In addition, there is no good solution to changing TSC speeds (informing all the guests about the TSC impending change before it happens would be a great deal of code and have issues with disobedient guests). This patch makes the host determine if the TSC is both constant and

Lguest currently requires a TSC, which breaks older machines and Matt Mackall who boots the host with "notsc". In addition, there is no good solution to changing TSC speeds (informing all the guests about the TSC impending change before it happens would be a great deal of code and have issues with disobedient guests). This patch makes the host determine if the TSC is both constant and

I am attaching a clocksource driver for HyperV. Signed-off-by: K. Y. Srinivasan <ksrinivasan at novell.com> -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: hyperv_clocksource.patch Url: http://lists.linux-foundation.org/pipermail/virtualization/attachments/20100405/80968881/attachment-0001.txt

I am attaching a clocksource driver for HyperV. Signed-off-by: K. Y. Srinivasan <ksrinivasan at novell.com> -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: hyperv_clocksource.patch Url: http://lists.linux-foundation.org/pipermail/virtualization/attachments/20100405/80968881/attachment-0001.txt

..._vector()); +} +#endif + +/** vmi clocksource */ + +static cycle_t read_real_cycles(void) +{ + return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL); +} + +static struct clocksource clocksource_vmi = { + .name = "vmi-timer", + .rating = 450, + .read = read_real_cycles, + .mask = CLOCKSOURCE_MASK(64), + .mult = 0, /* to be set */ + .shift = 22, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +static int __init init_vmi_clocksource(void) +{ + cycle_t cycles_per_msec; + + if (!vmi_timer_ops.get_cycle_frequency) + return 0; + /* Use khz2mult rather than hz2mult since hz arg is only 32-bits...

..._vector()); +} +#endif + +/** vmi clocksource */ + +static cycle_t read_real_cycles(void) +{ + return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL); +} + +static struct clocksource clocksource_vmi = { + .name = "vmi-timer", + .rating = 450, + .read = read_real_cycles, + .mask = CLOCKSOURCE_MASK(64), + .mult = 0, /* to be set */ + .shift = 22, + .flags = CLOCK_SOURCE_IS_CONTINUOUS, +}; + +static int __init init_vmi_clocksource(void) +{ + cycle_t cycles_per_msec; + + if (!vmi_timer_ops.get_cycle_frequency) + return 0; + /* Use khz2mult rather than hz2mult since hz arg is only 32-bits...

Matt attempted to add CLOCK_TAI support to the VDSO clock_gettime() implementation, which extended the clockid switch case and added yet another slightly different copy of the same code. Especially the extended switch case is problematic as the compiler tends to generate a jump table which then requires to use retpolines. If jump tables are disabled it adds yet another conditional to the existing

The following patches are the latest update of the TSC and hrtimer patches I posted on 29/03. Rusty's original TSC patch has been resynced to the latest lguest repo, as has the hrtimer patch, which also incorporates feedback from Jeremy & Rusty: - Change clock event hrtimer to absolute time. 'now' is captured in the host during the hypercall. - Propagate -ETIME back to the

The following patches are the latest update of the TSC and hrtimer patches I posted on 29/03. Rusty's original TSC patch has been resynced to the latest lguest repo, as has the hrtimer patch, which also incorporates feedback from Jeremy & Rusty: - Change clock event hrtimer to absolute time. 'now' is captured in the host during the hypercall. - Propagate -ETIME back to the

...cle_counter(VMI_CYCLES_AVAILABLE); +} + +static inline cycle_t read_stolen_cycles(void) +{ + return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_STOLEN); +} + +static struct clocksource clocksource_vmi = { + .name = "vmi-timer", + .rating = 450, + .read = read_real_cycles, + .mask = CLOCKSOURCE_MASK(64), + .mult = 0, /* to be set */ + .shift = 22, + .is_continuous = 1, +}; + + +/* Timer interrupt handler. */ +static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id); + +struct irqaction vmi_timer_irq = { + vmi_timer_interrupt, + SA_INTERRUPT, + CPU_MASK_NONE, + "VMI-alarm",...

...cle_counter(VMI_CYCLES_AVAILABLE); +} + +static inline cycle_t read_stolen_cycles(void) +{ + return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_STOLEN); +} + +static struct clocksource clocksource_vmi = { + .name = "vmi-timer", + .rating = 450, + .read = read_real_cycles, + .mask = CLOCKSOURCE_MASK(64), + .mult = 0, /* to be set */ + .shift = 22, + .is_continuous = 1, +}; + + +/* Timer interrupt handler. */ +static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id); + +struct irqaction vmi_timer_irq = { + vmi_timer_interrupt, + SA_INTERRUPT, + CPU_MASK_NONE, + "VMI-alarm",...

...cle_counter(VMI_CYCLES_AVAILABLE); +} + +static inline cycle_t read_stolen_cycles(void) +{ + return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_STOLEN); +} + +static struct clocksource clocksource_vmi = { + .name = "vmi-timer", + .rating = 450, + .read = read_real_cycles, + .mask = CLOCKSOURCE_MASK(64), + .mult = 0, /* to be set */ + .shift = 22, + .is_continuous = 1, +}; + + +/* Timer interrupt handler. */ +static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id); + +struct irqaction vmi_timer_irq = { + vmi_timer_interrupt, + SA_INTERRUPT, + CPU_MASK_NONE, + "VMI-alarm",...

...cle_counter(VMI_CYCLES_AVAILABLE); +} + +static inline cycle_t read_stolen_cycles(void) +{ + return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_STOLEN); +} + +static struct clocksource clocksource_vmi = { + .name = "vmi-timer", + .rating = 450, + .read = read_real_cycles, + .mask = CLOCKSOURCE_MASK(64), + .mult = 0, /* to be set */ + .shift = 22, + .is_continuous = 1, +}; + + +/* Timer interrupt handler. */ +static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id); + +struct irqaction vmi_timer_irq = { + vmi_timer_interrupt, + SA_INTERRUPT, + CPU_MASK_NONE, + "VMI-alarm",...

Matt attempted to add CLOCK_TAI support to the VDSO clock_gettime() implementation, which extended the clockid switch case and added yet another slightly different copy of the same code. Especially the extended switch case is problematic as the compiler tends to generate a jump table which then requires to use retpolines. If jump tables are disabled it adds yet another conditional to the existing

Matt attempted to add CLOCK_TAI support to the VDSO clock_gettime() implementation, which extended the clockid switch case and added yet another slightly different copy of the same code. Especially the extended switch case is problematic as the compiler tends to generate a jump table which then requires to use retpolines. If jump tables are disabled it adds yet another conditional to the existing

Hi Andi, This is a set of updates for the firstfloor patch queue. Quick rundown: revert-mm-x86_64-mm-account-for-module-percpu-space-separately-from-kernel-percpu.patch separate-module-percpu-space.patch Update the module percpu accounting patch fix-ff-allow-percpu-variables-to-be-page-aligned.patch Make sure the percpu memory allocation is page-aligned

Hi Andi, This is a set of updates for the firstfloor patch queue. Quick rundown: revert-mm-x86_64-mm-account-for-module-percpu-space-separately-from-kernel-percpu.patch separate-module-percpu-space.patch Update the module percpu accounting patch fix-ff-allow-percpu-variables-to-be-page-aligned.patch Make sure the percpu memory allocation is page-aligned

...es(struct clocksource *cs) -{ - cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL); - return max(ret, clocksource_vmi.cycle_last); -} - -static struct clocksource clocksource_vmi = { - .name = "vmi-timer", - .rating = 450, - .read = read_real_cycles, - .mask = CLOCKSOURCE_MASK(64), - .mult = 0, /* to be set */ - .shift = 22, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, -}; - -static int __init init_vmi_clocksource(void) -{ - cycle_t cycles_per_msec; - - if (!vmi_timer_ops.get_cycle_frequency) - return 0; - /* Use khz2mult rather than hz2mult since hz arg is only 32-bits...