search for: cur_tsc

On Thu, 9 Feb 2017, Vitaly Kuznetsov wrote: > +#ifdef CONFIG_HYPERV_TSCPAGE > +static notrace u64 vread_hvclock(int *mode) > +{ > + const struct ms_hyperv_tsc_page *tsc_pg = > + (const struct ms_hyperv_tsc_page *)&hvclock_page; > + u64 sequence, scale, offset, current_tick, cur_tsc; > + > + while (1) { > + sequence = READ_ONCE(tsc_pg->tsc_sequence); > + if (!sequence) > + break; > + > + scale = READ_ONCE(tsc_pg->tsc_scale); > + offset = READ_ONCE(tsc_pg->tsc_offset); > + rdtscll(cur_tsc); > + > + current_tick = mul_u64_u64_shr...

On Thu, 9 Feb 2017, Vitaly Kuznetsov wrote: > +#ifdef CONFIG_HYPERV_TSCPAGE > +static notrace u64 vread_hvclock(int *mode) > +{ > + const struct ms_hyperv_tsc_page *tsc_pg = > + (const struct ms_hyperv_tsc_page *)&hvclock_page; > + u64 sequence, scale, offset, current_tick, cur_tsc; > + > + while (1) { > + sequence = READ_ONCE(tsc_pg->tsc_sequence); > + if (!sequence) > + break; > + > + scale = READ_ONCE(tsc_pg->tsc_scale); > + offset = READ_ONCE(tsc_pg->tsc_offset); > + rdtscll(cur_tsc); > + > + current_tick = mul_u64_u64_shr...

...m/mshyperv.h > @@ -178,6 +178,56 @@ void hyperv_cleanup(void); > #endif > #ifdef CONFIG_HYPERV_TSCPAGE > struct ms_hyperv_tsc_page *hv_get_tsc_page(void); > +static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) > +{ > + u64 scale, offset, current_tick, cur_tsc; > + u32 sequence; > + > + /* > + * The protocol for reading Hyper-V TSC page is specified in Hypervisor > + * Top-Level Functional Specification ver. 3.0 and above. To get the > + * reference time we must do the following: > + * - READ ReferenceTscSequence > + * A sp...

...m/mshyperv.h > @@ -178,6 +178,56 @@ void hyperv_cleanup(void); > #endif > #ifdef CONFIG_HYPERV_TSCPAGE > struct ms_hyperv_tsc_page *hv_get_tsc_page(void); > +static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg) > +{ > + u64 scale, offset, current_tick, cur_tsc; > + u32 sequence; > + > + /* > + * The protocol for reading Hyper-V TSC page is specified in Hypervisor > + * Top-Level Functional Specification ver. 3.0 and above. To get the > + * reference time we must do the following: > + * - READ ReferenceTscSequence > + * A sp...

...t_tick = hv_read_tsc_page(tsc_pg); + + if (current_tick == U64_MAX) + rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick); - if (tsc_pg->tsc_sequence != 0) { - /* - * Use the tsc page to compute the value. - */ - - while (1) { - u64 tmp; - u32 sequence = tsc_pg->tsc_sequence; - u64 cur_tsc; - u64 scale = tsc_pg->tsc_scale; - s64 offset = tsc_pg->tsc_offset; - - rdtscll(cur_tsc); - /* current_tick = ((cur_tsc *scale) >> 64) + offset */ - asm("mulq %3" - : "=d" (current_tick), "=a" (tmp) - : "a" (cur_tsc), "r&quot...

...CONFIG_HYPERV_TSCPAGE >> > +static notrace u64 vread_hvclock(int *mode) >> > +{ >> > + const struct ms_hyperv_tsc_page *tsc_pg = >> > + (const struct ms_hyperv_tsc_page *)&hvclock_page; >> > + u64 sequence, scale, offset, current_tick, cur_tsc; >> > + >> > + while (1) { >> > + sequence = READ_ONCE(tsc_pg->tsc_sequence); >> > + if (!sequence) >> > + break; >> > + >> > + scale = READ_ONCE(tsc_pg->tsc_scale); >> >...

...CONFIG_HYPERV_TSCPAGE >> > +static notrace u64 vread_hvclock(int *mode) >> > +{ >> > + const struct ms_hyperv_tsc_page *tsc_pg = >> > + (const struct ms_hyperv_tsc_page *)&hvclock_page; >> > + u64 sequence, scale, offset, current_tick, cur_tsc; >> > + >> > + while (1) { >> > + sequence = READ_ONCE(tsc_pg->tsc_sequence); >> > + if (!sequence) >> > + break; >> > + >> > + scale = READ_ONCE(tsc_pg->tsc_scale); >> >...

Hi, merge window is about to close so I hope it's OK to make another try here. Changes since v2: - Add explicit READ_ONCE() to not rely on 'volatile' [Andy Lutomirski] - rdtsc() -> rdtsc_ordered() [Andy Lutomirski] - virt_rmb() -> smp_rmb() [Thomas Gleixner, Andy Lutomirski] Thomas, Andy, it seems the only blocker for the series was the ambiguity with TSC page read algorithm.

Hi, merge window is about to close so I hope it's OK to make another try here. Changes since v2: - Add explicit READ_ONCE() to not rely on 'volatile' [Andy Lutomirski] - rdtsc() -> rdtsc_ordered() [Andy Lutomirski] - virt_rmb() -> smp_rmb() [Thomas Gleixner, Andy Lutomirski] Thomas, Andy, it seems the only blocker for the series was the ambiguity with TSC page read algorithm.

...taly Kuznetsov wrote: >> +#ifdef CONFIG_HYPERV_TSCPAGE >> +static notrace u64 vread_hvclock(int *mode) >> +{ >> + const struct ms_hyperv_tsc_page *tsc_pg = >> + (const struct ms_hyperv_tsc_page *)&hvclock_page; >> + u64 sequence, scale, offset, current_tick, cur_tsc; >> + >> + while (1) { >> + sequence = READ_ONCE(tsc_pg->tsc_sequence); >> + if (!sequence) >> + break; >> + >> + scale = READ_ONCE(tsc_pg->tsc_scale); >> + offset = READ_ONCE(tsc_pg->tsc_offset); >> + rdtscll(cur_tsc); >>...

...sed if the 32-bit generated code was fine, too. > + > +static notrace u64 vread_hvclock(int *mode) > +{ > + const struct ms_hyperv_tsc_page *tsc_pg = > + (const struct ms_hyperv_tsc_page *)&pvclock_page; > + u64 sequence, scale, offset, current_tick, cur_tsc; > + > + while (1) { > + sequence = READ_ONCE(tsc_pg->tsc_sequence); > + if (!sequence) > + break; > + > + scale = READ_ONCE(tsc_pg->tsc_scale); > + offset = READ_ONCE(tsc_pg->tsc_of...

...sed if the 32-bit generated code was fine, too. > + > +static notrace u64 vread_hvclock(int *mode) > +{ > + const struct ms_hyperv_tsc_page *tsc_pg = > + (const struct ms_hyperv_tsc_page *)&pvclock_page; > + u64 sequence, scale, offset, current_tick, cur_tsc; > + > + while (1) { > + sequence = READ_ONCE(tsc_pg->tsc_sequence); > + if (!sequence) > + break; > + > + scale = READ_ONCE(tsc_pg->tsc_scale); > + offset = READ_ONCE(tsc_pg->tsc_of...

Hi, Hyper-V TSC page clocksource is suitable for vDSO, however, the protocol defined by the hypervisor is different from VCLOCK_PVCLOCK. I implemented the required support re-using pvclock_page VVAR. Simple sysbench test shows the following results: Before: # time sysbench --test=memory --max-requests=500000 run ... real 1m22.618s user 0m50.193s sys 0m32.268s After: # time sysbench

Hi, Hyper-V TSC page clocksource is suitable for vDSO, however, the protocol defined by the hypervisor is different from VCLOCK_PVCLOCK. I implemented the required support re-using pvclock_page VVAR. Simple sysbench test shows the following results: Before: # time sysbench --test=memory --max-requests=500000 run ... real 1m22.618s user 0m50.193s sys 0m32.268s After: # time sysbench

...uznetsov wrote: > > +#ifdef CONFIG_HYPERV_TSCPAGE > > +static notrace u64 vread_hvclock(int *mode) > > +{ > > + const struct ms_hyperv_tsc_page *tsc_pg = > > + (const struct ms_hyperv_tsc_page *)&hvclock_page; > > + u64 sequence, scale, offset, current_tick, cur_tsc; > > + > > + while (1) { > > + sequence = READ_ONCE(tsc_pg->tsc_sequence); > > + if (!sequence) > > + break; > > + > > + scale = READ_ONCE(tsc_pg->tsc_scale); > > + offset = READ_ONCE(tsc_pg->tsc_offset); > > + rdtscll(cur_tsc);...

...method On Thu, 9 Feb 2017, Vitaly Kuznetsov wrote: > +#ifdef CONFIG_HYPERV_TSCPAGE > +static notrace u64 vread_hvclock(int *mode) { > + const struct ms_hyperv_tsc_page *tsc_pg = > + (const struct ms_hyperv_tsc_page *)&hvclock_page; > + u64 sequence, scale, offset, current_tick, cur_tsc; > + > + while (1) { > + sequence = READ_ONCE(tsc_pg->tsc_sequence); > + if (!sequence) > + break; > + > + scale = READ_ONCE(tsc_pg->tsc_scale); > + offset = READ_ONCE(tsc_pg->tsc_offset); > + rdtscll(cur_tsc); > + > + current_tick = mul_u64_u64_shr...

Hi, Hyper-V TSC page clocksource is suitable for vDSO, however, the protocol defined by the hypervisor is different from VCLOCK_PVCLOCK. Implemented the required support. Simple sysbench test shows the following results: Before: # time sysbench --test=memory --max-requests=500000 run ... real 1m22.618s user 0m50.193s sys 0m32.268s After: # time sysbench --test=memory

Hi, Hyper-V TSC page clocksource is suitable for vDSO, however, the protocol defined by the hypervisor is different from VCLOCK_PVCLOCK. Implemented the required support. Simple sysbench test shows the following results: Before: # time sysbench --test=memory --max-requests=500000 run ... real 1m22.618s user 0m50.193s sys 0m32.268s After: # time sysbench --test=memory

...;> 32) + (p2 >> 32) + + ((((a_lo * b_lo) >> 32) + (u32)p1 + (u32)p2) >> 32); + +} + +static notrace u64 vread_hvclock(int *mode) +{ + const struct ms_hyperv_tsc_page *tsc_pg = + (const struct ms_hyperv_tsc_page *)&pvclock_page; + u64 sequence, scale, offset, current_tick, cur_tsc; + + while (1) { + sequence = READ_ONCE(tsc_pg->tsc_sequence); + if (!sequence) + break; + + scale = READ_ONCE(tsc_pg->tsc_scale); + offset = READ_ONCE(tsc_pg->tsc_offset); + rdtscll(cur_tsc); + + current_tick = mul64x64_hi(cur_tsc, scale) + offset; + + if (READ_ONCE(tsc_pg->ts...

Hi, while we're still waiting for a definitive ACK from Microsoft that the algorithm is good for SMP case (as we can't prevent the code in vdso from migrating between CPUs) I'd like to send v2 with some modifications to keep the discussion going. Changes since v1: - Document the TSC page reading protocol [Thomas Gleixner]. - Separate the TSC page reading code from