x86: kvm: Revert "remove sched notifier for cross-cpu migrations"

The following point:

2. per-CPU pvclock time info is updated if the
underlying CPU changes.

Is not true anymore since "KVM: x86: update pvclock area conditionally,
on cpu migration".

Add task migration notification back.

Problem noticed by Andy Lutomirski.

Signed-off-by: Marcelo Tosatti <[e-mail]>
CC: [e-mail] # 3.11+

arch/x86/include/asm/pvclock.h

···
 
 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)

arch/x86/kernel/pvclock.c

···
 	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
···
 
 	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(i) + (idx*PAGE_SIZE),
 			     PAGE_KERNEL_VVAR);
 	}
+
+
+	register_task_migration_notifier(&pvclock_migrate);
 
 	return 0;
 }

arch/x86/vdso/vclock_gettime.c

···
 	cycle_t ret;
 	u64 last;
 	u32 version;
+	u32 migrate_count;
 	u8 flags;
 	unsigned cpu, cpu1;
 
 
 	/*
-	 * 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.
-	 *
+	 * 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() & VGETCPU_CPU_MASK;
···
 		 */
 
 		pvti = get_pvti(cpu);
+
+		migrate_count = pvti->migrate_count;
 
 		version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
 
···
 		cpu1 = __getcpu() & VGETCPU_CPU_MASK;
 	} while (unlikely(cpu != cpu1 ||
 			  (pvti->pvti.version & 1) ||
-			  pvti->pvti.version != version));
+			  pvti->pvti.version != version ||
+			  pvti->migrate_count != migrate_count));
 
 	if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
 		*mode = VCLOCK_NONE;

include/linux/sched.h

···
 extern void calc_global_load(unsigned long ticks);
 extern void update_cpu_load_nohz(void);
 
+/* Notifier for when a task gets migrated to a new CPU */
+struct task_migration_notifier {
+	struct task_struct *task;
+	int from_cpu;
+	int to_cpu;
+};
+extern void register_task_migration_notifier(struct notifier_block *n);
+
 extern unsigned long get_parent_ip(unsigned long addr);
 
 extern void dump_cpu_task(int cpu);

kernel/sched/core.c

···
 		rq_clock_skip_update(rq, true);
 }
 
+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
+
+void register_task_migration_notifier(struct notifier_block *n)
+{
+	atomic_notifier_chain_register(&task_migration_notifier, n);
+}
+
 #ifdef CONFIG_SMP
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
···
 	trace_sched_migrate_task(p, new_cpu);
 
 	if (task_cpu(p) != new_cpu) {
+		struct task_migration_notifier tmn;
+
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
 		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+
+		tmn.task = p;
+		tmn.from_cpu = task_cpu(p);
+		tmn.to_cpu = new_cpu;
+
+		atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
 	}
 
 	__set_task_cpu(p, new_cpu);