x86: pvclock: Really remove the sched notifier for cross-cpu migrations

This reverts commits 0a4e6be9ca17c54817cf814b4b5aa60478c6df27
and 80f7fdb1c7f0f9266421f823964fd1962681f6ce.

The task migration notifier was originally introduced in order to support
the pvclock vsyscall with non-synchronized TSC, but KVM only supports it
with synchronized TSC.  Hence, on KVM the race condition is only needed
due to a bad implementation on the host side, and even then it's so rare
that it's mostly theoretical.

As far as KVM is concerned it's possible to fix the host, avoiding the
additional complexity in the vDSO and the (re)introduction of the task
migration notifier.

Xen, on the other hand, hasn't yet implemented vsyscall support at
all, so we do not care about its plans for non-synchronized TSC.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

5 files changed, 15 insertions, 87 deletions

diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 25b1cc07d496..d6b078e9fa28 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -95,7 +95,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
 
 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)
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index e5ecd20e72dd..2f355d229a58 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -141,46 +141,7 @@ 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
@@ -194,17 +155,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
 
 	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;
 }
 #endif
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 40d2473836c9..9793322751e0 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -82,15 +82,18 @@ static notrace cycle_t vread_pvclock(int *mode)
 	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.
+	 * 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.
+	 *
 	 */
 	do {
 		cpu = __getcpu() & VGETCPU_CPU_MASK;
@@ -99,27 +102,20 @@ static notrace cycle_t vread_pvclock(int *mode)
 		 * __getcpu() calls (Gleb).
 		 */
 
-		/* Make sure migrate_count will change if we leave the VCPU. */
-		do {
-			pvti = get_pvti(cpu);
-			migrate_count = pvti->migrate_count;
-
-			cpu1 = cpu;
-			cpu = __getcpu() & VGETCPU_CPU_MASK;
-		} while (unlikely(cpu != cpu1));
+		pvti = get_pvti(cpu);
 
 		version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
 
 		/*
 		 * Test we're still on the cpu as well as the version.
-		 * - We must read TSC of pvti's VCPU.
-		 * - KVM doesn't follow the versioning protocol, so data could
-		 *   change before version if we left the VCPU.
+		 * We could have been migrated just after the first
+		 * vgetcpu but before fetching the version, so we
+		 * wouldn't notice a version change.
 		 */
-		smp_rmb();
-	} while (unlikely((pvti->pvti.version & 1) ||
-			  pvti->pvti.version != version ||
-			  pvti->migrate_count != migrate_count));
+		cpu1 = __getcpu() & VGETCPU_CPU_MASK;
+	} while (unlikely(cpu != cpu1 ||
+			  (pvti->pvti.version & 1) ||
+			  pvti->pvti.version != version));
 
 	if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
 		*mode = VCLOCK_NONE;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8222ae40ecb0..26a2e6122734 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -175,14 +175,6 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 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);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f9123a82cbb6..fe22f7510bce 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1016,13 +1016,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 		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)
 {
@@ -1053,18 +1046,10 @@ 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);