diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-13 15:31:08 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-12-13 15:31:08 -0800 |
commit | 66cdd0ceaf65a18996f561b770eedde1d123b019 (patch) | |
tree | 4892eaa422d366fce5d1e866ff1fe0988af95569 /arch/x86/vdso | |
parent | 896ea17d3da5f44b2625c9cda9874d7dfe447393 (diff) | |
parent | 58b7825bc324da55415034a9f6ca5d716b8fd898 (diff) |
Merge tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Marcelo Tosatti:
"Considerable KVM/PPC work, x86 kvmclock vsyscall support,
IA32_TSC_ADJUST MSR emulation, amongst others."
Fix up trivial conflict in kernel/sched/core.c due to cross-cpu
migration notifier added next to rq migration call-back.
* tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (156 commits)
KVM: emulator: fix real mode segment checks in address linearization
VMX: remove unneeded enable_unrestricted_guest check
KVM: VMX: fix DPL during entry to protected mode
x86/kexec: crash_vmclear_local_vmcss needs __rcu
kvm: Fix irqfd resampler list walk
KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump
x86/kexec: VMCLEAR VMCSs loaded on all cpus if necessary
KVM: MMU: optimize for set_spte
KVM: PPC: booke: Get/set guest EPCR register using ONE_REG interface
KVM: PPC: bookehv: Add EPCR support in mtspr/mfspr emulation
KVM: PPC: bookehv: Add guest computation mode for irq delivery
KVM: PPC: Make EPCR a valid field for booke64 and bookehv
KVM: PPC: booke: Extend MAS2 EPN mask for 64-bit
KVM: PPC: e500: Mask MAS2 EPN high 32-bits in 32/64 tlbwe emulation
KVM: PPC: Mask ea's high 32-bits in 32/64 instr emulation
KVM: PPC: e500: Add emulation helper for getting instruction ea
KVM: PPC: bookehv64: Add support for interrupt handling
KVM: PPC: bookehv: Remove GET_VCPU macro from exception handler
KVM: PPC: booke: Fix get_tb() compile error on 64-bit
KVM: PPC: e500: Silence bogus GCC warning in tlb code
...
Diffstat (limited to 'arch/x86/vdso')
-rw-r--r-- | arch/x86/vdso/vclock_gettime.c | 81 | ||||
-rw-r--r-- | arch/x86/vdso/vgetcpu.c | 11 |
2 files changed, 81 insertions, 11 deletions
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 4df6c373421a..205ad328aa52 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -22,6 +22,7 @@ #include <asm/hpet.h> #include <asm/unistd.h> #include <asm/io.h> +#include <asm/pvclock.h> #define gtod (&VVAR(vsyscall_gtod_data)) @@ -62,6 +63,76 @@ static notrace cycle_t vread_hpet(void) return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0); } +#ifdef CONFIG_PARAVIRT_CLOCK + +static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu) +{ + const struct pvclock_vsyscall_time_info *pvti_base; + int idx = cpu / (PAGE_SIZE/PVTI_SIZE); + int offset = cpu % (PAGE_SIZE/PVTI_SIZE); + + BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END); + + pvti_base = (struct pvclock_vsyscall_time_info *) + __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx); + + return &pvti_base[offset]; +} + +static notrace cycle_t vread_pvclock(int *mode) +{ + const struct pvclock_vsyscall_time_info *pvti; + cycle_t ret; + u64 last; + u32 version; + u32 migrate_count; + u8 flags; + unsigned cpu, cpu1; + + + /* + * When looping to get a consistent (time-info, tsc) pair, we + * also need to deal with the possibility we can switch vcpus, + * so make sure we always re-fetch time-info for the current vcpu. + */ + do { + cpu = __getcpu() & VGETCPU_CPU_MASK; + /* TODO: We can put vcpu id into higher bits of pvti.version. + * This will save a couple of cycles by getting rid of + * __getcpu() calls (Gleb). + */ + + pvti = get_pvti(cpu); + + migrate_count = pvti->migrate_count; + + version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); + + /* + * Test we're still on the cpu as well as the version. + * We could have been migrated just after the first + * vgetcpu but before fetching the version, so we + * wouldn't notice a version change. + */ + cpu1 = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1 || + (pvti->pvti.version & 1) || + pvti->pvti.version != version || + pvti->migrate_count != migrate_count)); + + if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) + *mode = VCLOCK_NONE; + + /* refer to tsc.c read_tsc() comment for rationale */ + last = VVAR(vsyscall_gtod_data).clock.cycle_last; + + if (likely(ret >= last)) + return ret; + + return last; +} +#endif + notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; @@ -80,7 +151,7 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) } -notrace static inline u64 vgetsns(void) +notrace static inline u64 vgetsns(int *mode) { long v; cycles_t cycles; @@ -88,6 +159,10 @@ notrace static inline u64 vgetsns(void) cycles = vread_tsc(); else if (gtod->clock.vclock_mode == VCLOCK_HPET) cycles = vread_hpet(); +#ifdef CONFIG_PARAVIRT_CLOCK + else if (gtod->clock.vclock_mode == VCLOCK_PVCLOCK) + cycles = vread_pvclock(mode); +#endif else return 0; v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask; @@ -107,7 +182,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts) mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->wall_time_sec; ns = gtod->wall_time_snsec; - ns += vgetsns(); + ns += vgetsns(&mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); @@ -127,7 +202,7 @@ notrace static int do_monotonic(struct timespec *ts) mode = gtod->clock.vclock_mode; ts->tv_sec = gtod->monotonic_time_sec; ns = gtod->monotonic_time_snsec; - ns += vgetsns(); + ns += vgetsns(&mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq))); timespec_add_ns(ts, ns); diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c index 5463ad558573..2f94b039e55b 100644 --- a/arch/x86/vdso/vgetcpu.c +++ b/arch/x86/vdso/vgetcpu.c @@ -17,15 +17,10 @@ __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused) { unsigned int p; - if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) { - /* Load per CPU data from RDTSCP */ - native_read_tscp(&p); - } else { - /* Load per CPU data from GDT */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); - } + p = __getcpu(); + if (cpu) - *cpu = p & 0xfff; + *cpu = p & VGETCPU_CPU_MASK; if (node) *node = p >> 12; return 0; |