[PATCH] pvclock: introduce seqcount-like API

From: Paolo Bonzini
Date: Thu Jun 09 2016 - 07:23:32 EST


The version field in struct pvclock_vcpu_time_info basically implements
a seqcount. Wrap it with the usual read_begin and read_retry functions,
and use these APIs instead of peppering the code with smp_rmb()s.
While at it, change it to the more pedantically correct virt_rmb().

With this change, __pvclock_read_cycles can be simplified noticeably.

Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/entry/vdso/vclock_gettime.c | 25 +++++------------------
arch/x86/include/asm/pvclock.h | 39 +++++++++++++++++++++---------------
arch/x86/kernel/pvclock.c | 17 ++++++----------
3 files changed, 34 insertions(+), 47 deletions(-)

diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 2f02d23a05ef..94d54d0defa7 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -96,9 +96,8 @@ static notrace cycle_t vread_pvclock(int *mode)
{
const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
cycle_t ret;
- u64 tsc, pvti_tsc;
- u64 last, delta, pvti_system_time;
- u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift;
+ u64 last;
+ u32 version;

/*
* Note: The kernel and hypervisor must guarantee that cpu ID
@@ -123,29 +122,15 @@ static notrace cycle_t vread_pvclock(int *mode)
*/

do {
- version = pvti->version;
-
- smp_rmb();
+ version = pvclock_read_begin(pvti);

if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
*mode = VCLOCK_NONE;
return 0;
}

- tsc = rdtsc_ordered();
- pvti_tsc_to_system_mul = pvti->tsc_to_system_mul;
- pvti_tsc_shift = pvti->tsc_shift;
- pvti_system_time = pvti->system_time;
- pvti_tsc = pvti->tsc_timestamp;
-
- /* Make sure that the version double-check is last. */
- smp_rmb();
- } while (unlikely((version & 1) || version != pvti->version));
-
- delta = tsc - pvti_tsc;
- ret = pvti_system_time +
- pvclock_scale_delta(delta, pvti_tsc_to_system_mul,
- pvti_tsc_shift);
+ ret = __pvclock_read_cycles(pvti);
+ } while (pvclock_read_retry(pvti, version));

/* refer to vread_tsc() comment for rationale */
last = gtod->cycle_last;
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7c1c89598688..0ee92db1e9f3 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -25,6 +25,24 @@ void pvclock_resume(void);

void pvclock_touch_watchdogs(void);

+static __always_inline
+unsigned pvclock_read_begin(const struct pvclock_vcpu_time_info *src)
+{
+ unsigned version = src->version & ~1;
+ /* Make sure that the version is read before the data. */
+ virt_rmb();
+ return version;
+}
+
+static __always_inline
+bool pvclock_read_retry(const struct pvclock_vcpu_time_info *src,
+ unsigned version)
+{
+ /* Make sure that the version is re-read after the data. */
+ virt_rmb();
+ return version != src->version;
+}
+
/*
* Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
* yielding a 64-bit result.
@@ -69,23 +87,12 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
}

static __always_inline
-unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
- cycle_t *cycles, u8 *flags)
+cycle_t __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src)
{
- unsigned version;
- cycle_t offset;
- u64 delta;
-
- version = src->version;
- /* Make the latest version visible */
- smp_rmb();
-
- delta = rdtsc_ordered() - src->tsc_timestamp;
- offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
- src->tsc_shift);
- *cycles = src->system_time + offset;
- *flags = src->flags;
- return version;
+ u64 delta = rdtsc_ordered() - src->tsc_timestamp;
+ cycle_t offset = pvclock_scale_delta(delta, src->tsc_to_system_mul,
+ src->tsc_shift);
+ return src->system_time + offset;
}

struct pvclock_vsyscall_time_info {
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 06c58ce46762..3599404e3089 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -64,14 +64,9 @@ u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src)
u8 flags;

do {
- version = src->version;
- /* Make the latest version visible */
- smp_rmb();
-
+ version = pvclock_read_begin(src);
flags = src->flags;
- /* Make sure that the version double-check is last. */
- smp_rmb();
- } while ((src->version & 1) || version != src->version);
+ } while (pvclock_read_retry(src, version));

return flags & valid_flags;
}
@@ -84,10 +79,10 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
u8 flags;

do {
- version = __pvclock_read_cycles(src, &ret, &flags);
- /* Make sure that the version double-check is last. */
- smp_rmb();
- } while ((src->version & 1) || version != src->version);
+ version = pvclock_read_begin(src);
+ ret = __pvclock_read_cycles(src);
+ flags = src->flags;
+ } while (pvclock_read_retry(src, version));

if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) {
src->flags &= ~PVCLOCK_GUEST_STOPPED;
--
1.8.3.1