search for: vread_pvclock

...y), "g" (tv), "c" (tz) - : "memory", "edx"); - return ret; -} - #endif #ifdef CONFIG_PARAVIRT_CLOCK @@ -98,7 +73,7 @@ static notrace const struct pvclock_vsys return (const struct pvclock_vsyscall_time_info *)&pvclock_page; } -static notrace u64 vread_pvclock(int *mode) +static notrace u64 vread_pvclock(void) { const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; u64 ret; @@ -130,10 +105,8 @@ static notrace u64 vread_pvclock(int *mo do { version = pvclock_read_begin(pvti); - if (unlikely(!(pvti->flags & PVCLOCK_TSC_...

...-- arch/x86/entry/vdso/vclock_gettime.c | 39 ++++++----------------------------- 1 file changed, 7 insertions(+), 32 deletions(-) --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -76,9 +76,8 @@ static notrace const struct pvclock_vsys static notrace u64 vread_pvclock(void) { const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; - u64 ret; - u64 last; u32 version; + u64 ret; /* * Note: The kernel and hypervisor must guarantee that cpu ID @@ -111,13 +110,7 @@ static notrace u64 vread_pvclock(void) ret = __pvclock_read_cycles(pvti,...

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

...dso/vclock_gettime.c @@ -17,6 +17,7 @@ #include <asm/unistd.h> #include <asm/msr.h> #include <asm/pvclock.h> +#include <asm/mshyperv.h> #include <linux/math64.h> #include <linux/time.h> #include <linux/kernel.h> @@ -141,6 +142,49 @@ static notrace u64 vread_pvclock(int *mode) return last; } #endif +#ifdef CONFIG_HYPERV_CLOCK +/* (a * b) >> 64 implementation */ +static inline u64 mul64x64_hi(u64 a, u64 b) +{ + u64 a_lo, a_hi, b_lo, b_hi, p1, p2; + + a_lo = (u32)a; + a_hi = a >> 32; + b_lo = (u32)b; + b_hi = b >> 32; + p1 = a_lo * b_hi; +...

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

...(visibility("hidden"))); #endif +#ifdef CONFIG_HYPERV_TSCPAGE +extern u8 hvclock_page + __attribute__((visibility("hidden"))); +#endif + #ifndef BUILD_VDSO32 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) @@ -141,6 +147,32 @@ static notrace u64 vread_pvclock(int *mode) return last; } #endif +#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 =...

...gt; #include <asm/unistd.h> > #include <asm/msr.h> > #include <asm/pvclock.h> > +#include <asm/mshyperv.h> > #include <linux/math64.h> > #include <linux/time.h> > #include <linux/kernel.h> > @@ -141,6 +142,49 @@ static notrace u64 vread_pvclock(int *mode) > return last; > } > #endif > +#ifdef CONFIG_HYPERV_CLOCK > +/* (a * b) >> 64 implementation */ > +static inline u64 mul64x64_hi(u64 a, u64 b) > +{ > + u64 a_lo, a_hi, b_lo, b_hi, p1, p2; > + > + a_lo = (u32)a; > + a_hi =...

...gt; #include <asm/unistd.h> > #include <asm/msr.h> > #include <asm/pvclock.h> > +#include <asm/mshyperv.h> > #include <linux/math64.h> > #include <linux/time.h> > #include <linux/kernel.h> > @@ -141,6 +142,49 @@ static notrace u64 vread_pvclock(int *mode) > return last; > } > #endif > +#ifdef CONFIG_HYPERV_CLOCK > +/* (a * b) >> 64 implementation */ > +static inline u64 mul64x64_hi(u64 a, u64 b) > +{ > + u64 a_lo, a_hi, b_lo, b_hi, p1, p2; > + > + a_lo = (u32)a; > + a_hi =...

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

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, 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.

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

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