UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

x86/vdso: Move cycle_last handling into the caller 

Dereferencing gtod->cycle_last all over the place and foing the cycles <
last comparison in the vclock read functions generates horrible code. Doing
it at the call site is much better and gains a few cycles both for TSC and
pvclock.

Caveat: This adds the comparison to the hyperv vclock as well, but I have
no way to test that.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Matt Rickard <matt@softrans.com.au>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: devel@linuxdriverproject.org
Cc: virtualization@lists.linux-foundation.org
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Juergen Gross <jgross@suse.com>
Link: https://lkml.kernel.org/r/20180917130707.741440803@linutronix.de
This commit is contained in:
Thomas Gleixner 2018-09-17 14:45:43 +02:00
parent 4f72adc506
commit 3e89bf35eb
1 changed files with 7 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
arch/x86/entry/vdso/vclock_gettime.c
View File

@ -77,9 +77,8 @@ static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
static notrace u64 vread_pvclock(void) static notrace u64 vread_pvclock(void)
{ {
const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
u64 ret;
u64 last;
u32 version; u32 version;
u64 ret;
/* /*
* Note: The kernel and hypervisor must guarantee that cpu ID * Note: The kernel and hypervisor must guarantee that cpu ID
@ -112,13 +111,7 @@ static notrace u64 vread_pvclock(void)
ret = __pvclock_read_cycles(pvti, rdtsc_ordered()); ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
} while (pvclock_read_retry(pvti, version)); } while (pvclock_read_retry(pvti, version));
/* refer to vread_tsc() comment for rationale */ return ret;
last = gtod->cycle_last;
if (likely(ret >= last))
return ret;
return last;
} }
#endif #endif
#ifdef CONFIG_HYPERV_TSCPAGE #ifdef CONFIG_HYPERV_TSCPAGE
@ -131,30 +124,10 @@ static notrace u64 vread_hvclock(void)
} }
#endif #endif
notrace static u64 vread_tsc(void)
{
u64 ret = (u64)rdtsc_ordered();
u64 last = gtod->cycle_last;
if (likely(ret >= last))
return ret;
/*
* GCC likes to generate cmov here, but this branch is extremely
* predictable (it's just a function of time and the likely is
* very likely) and there's a data dependence, so force GCC
* to generate a branch instead. I don't barrier() because
* we don't actually need a barrier, and if this function
* ever gets inlined it will generate worse code.
*/
asm volatile ("");
return last;
}
notrace static inline u64 vgetcyc(int mode) notrace static inline u64 vgetcyc(int mode)
{ {
if (mode == VCLOCK_TSC) if (mode == VCLOCK_TSC)
return vread_tsc(); return (u64)rdtsc_ordered();
#ifdef CONFIG_PARAVIRT_CLOCK #ifdef CONFIG_PARAVIRT_CLOCK
else if (mode == VCLOCK_PVCLOCK) else if (mode == VCLOCK_PVCLOCK)
return vread_pvclock(); return vread_pvclock();
@ -169,17 +142,19 @@ notrace static inline u64 vgetcyc(int mode)
notrace static int do_hres(clockid_t clk, struct timespec *ts) notrace static int do_hres(clockid_t clk, struct timespec *ts)
{ {
struct vgtod_ts *base = &gtod->basetime[clk]; struct vgtod_ts *base = &gtod->basetime[clk];
u64 cycles, last, ns;
unsigned int seq; unsigned int seq;
u64 cycles, ns;
do { do {
seq = gtod_read_begin(gtod); seq = gtod_read_begin(gtod);
ts->tv_sec = base->sec; ts->tv_sec = base->sec;
ns = base->nsec; ns = base->nsec;
last = gtod->cycle_last;
cycles = vgetcyc(gtod->vclock_mode); cycles = vgetcyc(gtod->vclock_mode);
if (unlikely((s64)cycles < 0)) if (unlikely((s64)cycles < 0))
return vdso_fallback_gettime(clk, ts); return vdso_fallback_gettime(clk, ts);
ns += (cycles - gtod->cycle_last) * gtod->mult; if (cycles > last)
ns += (cycles - last) * gtod->mult;
ns >>= gtod->shift; ns >>= gtod->shift;
} while (unlikely(gtod_read_retry(gtod, seq))); } while (unlikely(gtod_read_retry(gtod, seq)));