x86: pvclock: generic pvclock vsyscall initialization

Originally from Jeremy Fitzhardinge.

Introduce generic, non hypervisor specific, pvclock initialization
routines.

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

4 files changed, 91 insertions, 0 deletions

diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index 0bdbbb3b9ce7..16a57f4ed64d 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/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;
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 4da3c0c4c974..a09c28571064 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/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
+	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
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 63f91679af73..109a9dd5d454 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -91,4 +91,16 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 	return version;
 }
 
+struct pvclock_vsyscall_time_info {
+	struct pvclock_vcpu_time_info pvti;
+	u32 migrate_count;
+} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+
+#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
+#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1)
+
+int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
+				 int size);
+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu);
+
 #endif /* _ASM_X86_PVCLOCK_H */
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index c8fb043a8695..85c39590c1a4 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -17,6 +17,11 @@
 
 #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/fixmap.h>
 #include <asm/pvclock.h>
 
 static u8 valid_flags __read_mostly = 0;
@@ -122,3 +127,71 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
 
 	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
 }
+
+static struct pvclock_vsyscall_time_info *pvclock_vdso_info;
+
+static struct pvclock_vsyscall_time_info *
+pvclock_get_vsyscall_user_time_info(int cpu)
+{
+	if (!pvclock_vdso_info) {
+		BUG();
+		return NULL;
+	}
+
+	return &pvclock_vdso_info[cpu];
+}
+
+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
+{
+	return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
+}
+
+#ifdef CONFIG_X86_64
+static 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);
+
+	/* this is NULL when pvclock vsyscall is not initialized */
+	if (unlikely(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(struct pvclock_vsyscall_time_info *i,
+				 int size)
+{
+	int idx;
+
+	WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
+
+	pvclock_vdso_info = i;
+
+	for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
+		__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
+			     __pa_symbol(i) + (idx*PAGE_SIZE),
+			     PAGE_KERNEL_VVAR);
+	}
+
+
+	register_task_migration_notifier(&pvclock_migrate);
+
+	return 0;
+}
+#endif