x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader

The pvclock vdso code was too abstracted to understand easily
and excessively paranoid.  Simplify it for a huge speedup.

This opens the door for additional simplifications, as the vdso
no longer accesses the pvti for any vcpu other than vcpu 0.

Before, vclock_gettime using kvm-clock took about 45ns on my
machine. With this change, it takes 29ns, which is almost as
fast as the pure TSC implementation.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/6b51dcc41f1b101f963945c5ec7093d72bdac429.1449702533.git.luto@kernel.orgSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/vdso/vclock_gettime.c

@@ -78,47 +78,58 @@ static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
 
 static notrace cycle_t vread_pvclock(int *mode)
 {
-	const struct pvclock_vsyscall_time_info *pvti;
+	const struct pvclock_vcpu_time_info *pvti = &get_pvti(0)->pvti;
 	cycle_t ret;
-	u64 last;
-	u32 version;
-	u8 flags;
-	unsigned cpu, cpu1;
-
+	u64 tsc, pvti_tsc;
+	u64 last, delta, pvti_system_time;
+	u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift;
 
 	/*
-	 * Note: hypervisor must guarantee that:
-	 * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
-	 * 2. that per-CPU pvclock time info is updated if the
-	 *    underlying CPU changes.
-	 * 3. that version is increased whenever underlying CPU
-	 *    changes.
+	 * Note: The kernel and hypervisor must guarantee that cpu ID
+	 * number maps 1:1 to per-CPU pvclock time info.
+	 *
+	 * Because the hypervisor is entirely unaware of guest userspace
+	 * preemption, it cannot guarantee that per-CPU pvclock time
+	 * info is updated if the underlying CPU changes or that that
+	 * version is increased whenever underlying CPU changes.
 	 *
+	 * On KVM, we are guaranteed that pvti updates for any vCPU are
+	 * atomic as seen by *all* vCPUs.  This is an even stronger
+	 * guarantee than we get with a normal seqlock.
+	 *
+	 * On Xen, we don't appear to have that guarantee, but Xen still
+	 * supplies a valid seqlock using the version field.
+
+	 * We only do pvclock vdso timing at all if
+	 * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+	 * mean that all vCPUs have matching pvti and that the TSC is
+	 * synced, so we can just look at vCPU 0's pvti.
 	 */
+
+	if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
+		*mode = VCLOCK_NONE;
+		return 0;
+	}
+
 	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).
-		 */
+		version = pvti->version;
 
-		pvti = get_pvti(cpu);
+		/* This is also a read barrier, so we'll read version first. */
+		tsc = rdtsc_ordered();
 
-		version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
+		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;
 
-		/*
-		 * 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));
+		/* Make sure that the version double-check is last. */
+		smp_rmb();
+	} while (unlikely((version & 1) || version != pvti->version));
 
-	if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
-		*mode = VCLOCK_NONE;
+	delta = tsc - pvti_tsc;
+	ret = pvti_system_time +
+		pvclock_scale_delta(delta, pvti_tsc_to_system_mul,
+				    pvti_tsc_shift);
 
 	/* refer to tsc.c read_tsc() comment for rationale */
 	last = gtod->cycle_last;