From mboxrd@z Thu Jan  1 00:00:00 1970
From: Marcelo Tosatti <mtosatti@redhat.com>
Subject: [patch 12/18] x86: vdso: pvclock gettime support
Date: Wed, 24 Oct 2012 11:13:52 -0200
Message-ID: <20121024131621.840274360@redhat.com>
References: <20121024131340.742340256@redhat.com>
Cc: johnstul@us.ibm.com, jeremy@goop.org, glommer@parallels.com,
	zamsden@gmail.com, gleb@redhat.com, avi@redhat.com,
	pbonzini@redhat.com, Marcelo Tosatti <mtosatti@redhat.com>
To: kvm@vger.kernel.org
Return-path: <kvm-owner@vger.kernel.org>
Received: from mx1.redhat.com ([209.132.183.28]:37532 "EHLO mx1.redhat.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1756466Ab2JXNRD (ORCPT <rfc822;kvm@vger.kernel.org>);
	Wed, 24 Oct 2012 09:17:03 -0400
Content-Disposition: inline; filename=10-add-pvclock-vdso-code
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

Improve performance of time system calls when using Linux pvclock, 
by reading time info from fixmap visible copy of pvclock data.

Originally from Jeremy Fitzhardinge.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Index: vsyscall/arch/x86/vdso/vclock_gettime.c
===================================================================
--- vsyscall.orig/arch/x86/vdso/vclock_gettime.c
+++ vsyscall/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 +63,69 @@ static notrace cycle_t vread_hpet(void)
 	return readl((const void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
 }
 
+#ifdef CONFIG_PARAVIRT_CLOCK_VSYSCALL
+
+static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
+{
+	const aligned_pvti_t *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 = (aligned_pvti_t *)__fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx);
+
+	return &pvti_base[offset].info;
+}
+
+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() & 0xfff;
+		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() & 0xfff;
+	} 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;
+
+	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;
@@ -88,6 +152,8 @@ notrace static inline u64 vgetsns(int *m
 		cycles = vread_tsc();
 	else if (gtod->clock.vclock_mode == VCLOCK_HPET)
 		cycles = vread_hpet();
+	else if (gtod->clock.vclock_mode == VCLOCK_PVCLOCK)
+		cycles = vread_pvclock(mode);
 	else
 		return 0;
 	v = (cycles - gtod->clock.cycle_last) & gtod->clock.mask;
Index: vsyscall/arch/x86/include/asm/vsyscall.h
===================================================================
--- vsyscall.orig/arch/x86/include/asm/vsyscall.h
+++ vsyscall/arch/x86/include/asm/vsyscall.h
@@ -33,6 +33,21 @@ extern void map_vsyscall(void);
  */
 extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
 
+static inline unsigned int __getcpu(void)
+{
+	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));
+	}
+
+	return p;
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_VSYSCALL_H */
Index: vsyscall/arch/x86/vdso/vgetcpu.c
===================================================================
--- vsyscall.orig/arch/x86/vdso/vgetcpu.c
+++ vsyscall/arch/x86/vdso/vgetcpu.c
@@ -17,13 +17,8 @@ __vdso_getcpu(unsigned *cpu, unsigned *n
 {
 	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;
 	if (node)