Originally from Jeremy Fitzhardinge.
Introduce generic, non hypervisor specific, pvclock initialization
routines.
Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>
Index: vsyscall/arch/x86/kernel/pvclock.c
===================================================================
--- vsyscall.orig/arch/x86/kernel/pvclock.c
+++ vsyscall/arch/x86/kernel/pvclock.c
@@ -17,6 +17,10 @@
#include <linux/kernel.h>
#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/sched.h>
+#include <linux/gfp.h>
+#include <linux/bootmem.h>
#include <asm/pvclock.h>
static u8 valid_flags __read_mostly = 0;
@@ -122,3 +126,70 @@ void pvclock_read_wallclock(struct pvclo
set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
}
+
+#ifdef CONFIG_PARAVIRT_CLOCK_VSYSCALL
+
+static aligned_pvti_t *pvclock_vdso_info;
+
+static struct pvclock_vsyscall_time_info *pvclock_get_vsyscall_user_time_info(int cpu)
+{
+ if (pvclock_vdso_info == NULL) {
+ BUG();
+ return NULL;
+ }
+
+ return &pvclock_vdso_info[cpu].info;
+}
+
+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
+{
+ return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
+}
+
+int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, void *v)
+{
+ struct task_migration_notifier *mn = v;
+ struct pvclock_vsyscall_time_info *pvti;
+
+ pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu);
+
+ if (pvti == NULL)
+ return NOTIFY_DONE;
+
+ pvti->migrate_count++;
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block pvclock_migrate = {
+ .notifier_call = pvclock_task_migrate,
+};
+
+/*
+ * Initialize the generic pvclock vsyscall state. This will allocate
+ * a/some page(s) for the per-vcpu pvclock information, set up a
+ * fixmap mapping for the page(s)
+ */
+int __init pvclock_init_vsyscall(void)
+{
+ int idx;
+ unsigned int size = PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE;
+
+ pvclock_vdso_info = __alloc_bootmem(size, PAGE_SIZE, 0);
+ if (!pvclock_vdso_info)
+ return -ENOMEM;
+
+ memset(pvclock_vdso_info, 0, size);
+
+ for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
+ __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
+ __pa_symbol(pvclock_vdso_info) + (idx*PAGE_SIZE),
+ PAGE_KERNEL_VVAR);
+ }
+
+ register_task_migration_notifier(&pvclock_migrate);
+
+ return 0;
+}
+
+#endif /* CONFIG_PARAVIRT_CLOCK_VSYSCALL */
Index: vsyscall/arch/x86/include/asm/fixmap.h
===================================================================
--- vsyscall.orig/arch/x86/include/asm/fixmap.h
+++ vsyscall/arch/x86/include/asm/fixmap.h
@@ -19,6 +19,7 @@
#include <asm/acpi.h>
#include <asm/apicdef.h>
#include <asm/page.h>
+#include <asm/pvclock.h>
#ifdef CONFIG_X86_32
#include <linux/threads.h>
#include <asm/kmap_types.h>
@@ -81,6 +82,10 @@ enum fixed_addresses {
VVAR_PAGE,
VSYSCALL_HPET,
#endif
+#ifdef CONFIG_PARAVIRT_CLOCK_VSYSCALL
+ PVCLOCK_FIXMAP_BEGIN,
+ PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
+#endif
FIX_DBGP_BASE,
FIX_EARLYCON_MEM_BASE,
#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
Index: vsyscall/arch/x86/include/asm/pvclock.h
===================================================================
--- vsyscall.orig/arch/x86/include/asm/pvclock.h
+++ vsyscall/arch/x86/include/asm/pvclock.h
@@ -13,6 +13,8 @@ void pvclock_read_wallclock(struct pvclo
struct pvclock_vcpu_time_info *vcpu,
struct timespec *ts);
void pvclock_resume(void);
+int __init pvclock_init_vsyscall(void);
+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu);
/*
* Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
@@ -85,4 +87,24 @@ unsigned __pvclock_read_cycles(const str
return version;
}
+#ifdef CONFIG_PARAVIRT_CLOCK_VSYSCALL
+
+struct pvclock_vsyscall_time_info {
+ struct pvclock_vcpu_time_info pvti;
+ u32 migrate_count;
+};
+
+typedef union {
+ struct pvclock_vsyscall_time_info info;
+ char pad[SMP_CACHE_BYTES];
+} aligned_pvti_t ____cacheline_aligned;
+
+#define PVTI_SIZE sizeof(aligned_pvti_t)
+#if NR_CPUS == 1
+#define PVCLOCK_VSYSCALL_NR_PAGES 1
+#else
+#define PVCLOCK_VSYSCALL_NR_PAGES ((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1
+#endif
+#endif /* CONFIG_PARAVIRT_CLOCK_VSYSCALL */
+
#endif /* _ASM_X86_PVCLOCK_H */
Index: vsyscall/arch/x86/include/asm/clocksource.h
===================================================================
--- vsyscall.orig/arch/x86/include/asm/clocksource.h
+++ vsyscall/arch/x86/include/asm/clocksource.h
@@ -8,6 +8,7 @@
#define VCLOCK_NONE 0 /* No vDSO clock available. */
#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */
#define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */
+#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */
struct arch_clocksource_data {
int vclock_mode;
Index: vsyscall/arch/x86/Kconfig
===================================================================
--- vsyscall.orig/arch/x86/Kconfig
+++ vsyscall/arch/x86/Kconfig
@@ -632,6 +632,13 @@ config PARAVIRT_SPINLOCKS
config PARAVIRT_CLOCK
bool
+config PARAVIRT_CLOCK_VSYSCALL
+ bool "Paravirt clock vsyscall support"
+ depends on PARAVIRT_CLOCK && GENERIC_TIME_VSYSCALL
+ ---help---
+ Enable performance critical clock related system calls to
+ be executed in userspace, provided that the hypervisor
+ supports it.
endif
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
